ML + Vision Top-6 Agent Survey - ICML 2025 - Page 1 of 4¶
- Venue: International Conference on Machine Learning
- Year: 2025
- Page: 1 / 4
- Papers: 1-30 / 98
Papers
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents Paper
Abstract
Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks. While language-centric embodied agents have garnered substantial attention, MLLM-based embodied agents remain underexplored due to the lack of comprehensive evaluation frameworks. To bridge this gap, we introduce EmbodiedBench, an extensive benchmark designed to evaluate vision-driven embodied agents. EmbodiedBench features: (1) a diverse set of 1,128 testing tasks across four environments, ranging from high-level semantic tasks (e.g., household) to low-level tasks involving atomic actions (e.g., navigation and manipulation); and (2) six meticulously curated subsets evaluating essential agent capabilities like commonsense reasoning, complex instruction understanding, spatial awareness, visual perception, and long-term planning. Through extensive experiments, we evaluated 24 leading proprietary and open-source MLLMs within EmbodiedBench. Our findings reveal that: MLLMs excel at high-level tasks but struggle with low-level manipulation, with the best model, GPT-4o, scoring only 28.9% on average. EmbodiedBench provides a multifaceted standardized evaluation platform that not only highlights existing challenges but also offers valuable insights to advance MLLM-based embodied agents. Our code and dataset are available at https://embodiedbench.github.io.
Claim
Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks.
UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent Paper
Abstract
Recent advancements in Vision-Language-Action (VLA) models have leveraged pre-trained Vision-Language Models (VLMs) to improve the generalization capabilities. VLMs, typically pre-trained on vision-language understanding tasks, provide rich semantic knowledge and reasoning abilities. However, prior research has shown that VLMs often focus on high-level semantic content and neglect low-level features, limiting their ability to capture detailed spatial information and understand physical dynamics. These aspects, which are crucial for embodied control tasks, remain underexplored in existing pre-training paradigms. In this paper, we investigate the training paradigm for VLAs, and introduce UP-VLA, a Unified VLA model training with both multi-modal Understanding and future Prediction objectives, enhancing both high-level semantic comprehension and low-level spatial understanding. Experimental results show that UP-VLA achieves a 33% improvement on the Calvin ABC-D benchmark compared to the previous state-of-the-art method. Additionally, UP-VLA demonstrates improved success rates in real-world manipulation tasks, particularly those requiring precise spatial information.
Claim
Recent advancements in Vision-Language-Action (VLA) models have leveraged pre-trained Vision-Language Models (VLMs) to improve the generalization capabilities.
OrcaLoca: An LLM Agent Framework for Software Issue Localization Paper
Abstract
Recent developments in Large Language Model (LLM) agents are revolutionizing Autonomous Software Engineering (ASE), enabling automated coding, problem fixes, and feature improvements. However, localization -- precisely identifying software problems by navigating to relevant code sections -- remains a significant challenge. Current approaches often yield suboptimal results due to a lack of effective integration between LLM agents and precise code search mechanisms. This paper introduces OrcaLoca, an LLM agent framework that improves accuracy for software issue localization by integrating priority-based scheduling for LLM-guided action, action decomposition with relevance scoring, and distance-aware context pruning. Experimental results demonstrate that OrcaLoca becomes the new open-source state-of-the-art (SOTA) in function match rate (65.33%) on SWE-bench Lite. It also improves the final resolved rate of an open-source framework by 6.33 percentage points through its patch generation integration.
Claim
Recent developments in Large Language Model (LLM) agents are revolutionizing Autonomous Software Engineering (ASE), enabling automated coding, problem fixes, and feature improvements.
Automated Hypothesis Validation with Agentic Sequential Falsifications Paper
Abstract
Hypotheses are central to information acquisition, decision-making, and discovery. However, many real-world hypotheses are abstract, high-level statements that are difficult to validate directly. This challenge is further intensified by the rise of hypothesis generation from Large Language Models (LLMs), which are prone to hallucination and produce hypotheses in volumes that make manual validation impractical. Here we propose Popper, an agentic framework for rigorous automated validation of free-form hypotheses. Guided by Karl Popper's principle of falsification, Popper validates a hypothesis using LLM agents that design and execute falsification experiments targeting its measurable implications. A novel sequential testing framework ensures strict Type-I error control while actively gathering evidence from diverse observations, whether drawn from existing data or newly conducted procedures. We demonstrate Popper on six domains including biology, economics, and sociology. Popper delivers robust error control, high power, and scalability. Furthermore, compared to human scientists, Popper achieved comparable performance in validating complex biological hypotheses while reducing time by 10 folds, providing a scalable, rigorous solution for hypothesis validation.
Claim
Hypotheses are central to information acquisition, decision-making, and discovery.
PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification Paper
Abstract
Recent research builds various patching agents that combine large language models (LLMs) with non-ML tools and achieve promising results on the state-of-the-art (SOTA) software patching benchmark, SWE-bench. Based on how to determine the patching workflows, existing patching agents can be categorized as agent-based planning methods, which rely on LLMs for planning, and rule-based planning methods, which follow a pre-defined workflow. At a high level, agent-based planning methods achieve high patching performance but with a high cost and limited stability. Rule-based planning methods, on the other hand, are more stable and efficient but have key workflow limitations that compromise their patching performance. In this paper, we propose PatchPilot, an agentic patcher that strikes a balance between patching efficacy, stability, and cost-efficiency. PatchPilot proposes a novel rule-based planning workflow with five components: reproduction, localization, generation, validation, and refinement (where refinement is unique to PatchPilot). We introduce novel and customized designs to each component to optimize their effectiveness and efficiency. Through extensive experiments on the SWE-bench benchmarks, PatchPilot shows a superior performance than existing open-source methods while maintaining low cost (less than 1$ per instance) and ensuring higher stability. We also conduct a detailed ablation study to validate the key designs in each component. Our code is available at https://github.com/ucsb-mlsec/PatchPilot.
Claim
Recent research builds various patching agents that combine large language models (LLMs) with non-ML tools and achieve promising results on the state-of-the-art (SOTA) software patching benchmark, SWE-bench.
Adaptive Self-improvement LLM Agentic System for ML Library Development Paper
Abstract
ML libraries, often written in architecture-specific programming languages (ASPLs) that target domain-specific architectures, are key to efficient ML systems. However, writing these high-performance ML libraries is challenging because it requires expert knowledge of ML algorithms and the ASPL. Large language models (LLMs), on the other hand, have shown general coding capabilities. However, challenges remain when using LLMs for generating ML libraries using ASPLs because 1) this task is complicated even for experienced human programmers and 2) there are limited code examples because of the esoteric and evolving nature of ASPLs. Therefore, LLMs need complex reasoning with limited data in order to complete this task. To address these challenges, we introduce an adaptive self-improvement agentic system. In order to evaluate the effectiveness of our system, we construct a benchmark of a typical ML library and generate ASPL code with both open and closed-source LLMs on this benchmark. Our results show improvements of up to \(3.9\times\) over a baseline single LLM.
Claim
ML libraries, often written in architecture-specific programming languages (ASPLs) that target domain-specific architectures, are key to efficient ML systems.
Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning Paper
Abstract
Online fine-tuning vision-language model (VLM) agents with reinforcement learning (RL) has shown promise for equipping agents with multi-step, goal-oriented capabilities in dynamic environments. However, their open-ended textual action space and non-end-to-end nature of action generation present significant challenges to effective online exploration in RL, e.g., explosion of the exploration space. We propose a novel online fine-tuning method, Counterfactual Soft Reinforcement Learning (CoSo), better suited to the textual output space of VLM agents. Compared to prior methods that assign uniform uncertainty to all tokens, CoSo leverages counterfactual reasoning to dynamically assess the causal influence of individual tokens on post-processed actions. By prioritizing the exploration of action-critical tokens while reducing the impact of semantically redundant or low-impact tokens, CoSo enables a more targeted and efficient online rollout process. We provide theoretical analysis proving CoSo's convergence and policy improvement guarantees, and extensive empirical evaluations supporting CoSo's effectiveness. Our results across a diverse set of agent tasks, including Android device control, card gaming, and embodied AI, highlight its remarkable ability to enhance exploration efficiency and deliver consistent performance gains. The code is available at https://github.com/langfengQ/CoSo.
Claim
Online fine-tuning vision-language model (VLM) agents with reinforcement learning (RL) has shown promise for equipping agents with multi-step, goal-oriented capabilities in dynamic environments.
UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning Paper
Abstract
Large Language Model (LLM) agents equipped with external tools have become increasingly powerful for complex tasks such as web shopping, automated email replies, and financial trading. However, these advancements amplify the risks of adversarial attacks, especially when agents can access sensitive external functionalities. Nevertheless, manipulating LLM agents into performing targeted malicious actions or invoking specific tools remains challenging, as these agents extensively reason or plan before executing final actions. In this work, we present UDora, a unified red teaming framework designed for LLM agents that dynamically hijacks the agent's reasoning processes to compel malicious behavior. Specifically, UDora first generates the model's reasoning trace for the given task, then automatically identifies optimal points within this trace to insert targeted perturbations. The resulting perturbed reasoning is then used as a surrogate response for optimization. By iteratively applying this process, the LLM agent will then be induced to undertake designated malicious actions or to invoke specific malicious tools. Our approach demonstrates superior effectiveness compared to existing methods across three LLM agent datasets. The code is available at https://github.com/AI-secure/UDora.
Claim
Large Language Model (LLM) agents equipped with external tools have become increasingly powerful for complex tasks such as web shopping, automated email replies, and financial trading.
Nemotron-CORTEXA: Enhancing LLM Agents for Software Engineering Tasks via Improved Localization and Solution Diversity Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
Guided Search Strategies in Non-Serializable Environments with Applications to Software Engineering Agents Paper
Abstract
Large language models (LLMs) have recently achieved remarkable results in complex multi-step tasks, such as mathematical reasoning and agentic software engineering. However, they often struggle to maintain consistent performance across multiple solution attempts. One effective approach to narrow the gap between average-case and best-case performance is guided test-time search, which explores multiple solution paths to identify the most promising one. Unfortunately, effective search techniques (e.g. MCTS) are often unsuitable for non-serializable RL environments, such as Docker containers, where intermediate environment states cannot be easily saved and restored. We investigate two complementary search strategies applicable to such environments: 1-step lookahead and trajectory selection, both guided by a learned action-value function estimator. On the SWE-bench Verified benchmark, a key testbed for agentic software engineering, we find these methods to double the average success rate of a fine-tuned Qwen-72B model, achieving 40.8%, the new state-of-the-art for open-weights models. Additionally, we show that these techniques are transferable to more advanced closed models, yielding similar improvements with GPT-4o.
Claim
Large language models (LLMs) have recently achieved remarkable results in complex multi-step tasks, such as mathematical reasoning and agentic software engineering.
SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering Paper
Abstract
Software engineering (SE) is increasingly collaborative, with developers working together on shared complex codebases. Effective collaboration in shared environments requires participants -- whether humans or AI agents -- to stay on the same page as their environment evolves. When a collaborator's understanding diverges from the current state -- what we term the out-of-sync challenge -- the collaborator's actions may fail, leading to integration issues. In this work, we introduce SyncMind, a framework that systematically defines the out-of-sync problem faced by large language model (LLM) agents in collaborative software engineering (CSE). Based on SyncMind, we create SyncBench, a benchmark featuring 24,332 instances of agent out-of-sync scenarios in real-world CSE derived from 21 popular GitHub repositories with executable verification tests. Experiments on SyncBench uncover critical insights into existing LLM agents' capabilities and limitations. Besides substantial performance gaps among agents (from Llama-3.1 agent<= 3.33% to Claude-3.5-Sonnet>= 28.18%), their consistently low collaboration willingness (<= 4.86%) suggests fundamental limitations of existing LLM in CSE. However, when collaboration occurs, it positively correlates with out-of-sync recovery success. Minimal performance differences in agents' resource-aware out-of-sync recoveries further reveal their significant lack of resource awareness and adaptability, shedding light on future resource-efficient collaborative systems. Code and data are openly available on our project website: https://xhguo7.github.io/SyncMind/.
Claim
Software engineering (SE) is increasingly collaborative, with developers working together on shared complex codebases.
The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models Paper
Abstract
Not stated in metadata.
Claim
Not stated in abstract.
Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark Paper
Abstract
The ability to organically reason over and with both text and images is a pillar of human intelligence, yet the ability of Multimodal Large Language Models (MLLMs) to perform such multimodal reasoning remains under-explored. Existing benchmarks often emphasize text-dominant reasoning or rely on shallow visual cues, failing to adequately assess integrated visual and textual reasoning. We introduce EMMA (Enhanced MultiModal reAsoning), a benchmark targeting organic multimodal reasoning across mathematics, physics, chemistry, and coding. EMMA tasks demand advanced cross-modal reasoning that cannot be addressed by reasoning independently in each modality, offering an enhanced test suite for MLLMs' reasoning capabilities. Our evaluation of state-of-the-art MLLMs on EMMA reveals significant limitations in handling complex multimodal and multi-step reasoning tasks, even with advanced techniques like Chain-of-Thought prompting and test-time compute scaling underperforming. These findings underscore the need for improved multimodal architectures and training paradigms to close the gap between human and model reasoning in multimodality.
Claim
The ability to organically reason over and with both text and images is a pillar of human intelligence, yet the ability of Multimodal Large Language Models (MLLMs) to perform such multimodal reasoning remains under-explored.
Multi-agent Architecture Search via Agentic Supernet Paper
Abstract
Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents through disciplined collaboration and interaction, while constructing these systems often requires labor-intensive manual designs. Despite the availability of methods to automate the design of agentic workflows, they typically seek to identify a static, complex, one-size-fits-all system, which, however, fails to dynamically allocate inference resources based on the difficulty and domain of each query. To address this challenge, we shift away from the pursuit of a monolithic agentic system, instead optimizing the agentic supernet, a probabilistic and continuous distribution of agentic architectures. We introduce MaAS, an automated framework that samples query-dependent agentic systems from the supernet, delivering high-quality solutions and tailored resource allocation (e.g., LLM calls, tool calls, token cost). Comprehensive evaluation across six benchmarks demonstrates that MaAS (I) requires only \(6\sim45%\) of the inference costs of existing handcrafted or automated multi-agent systems, (II) surpasses them by \(0.54%\sim11.82%\), and (III) enjoys superior cross-dataset and cross-LLM-backbone transferability.
Claim
Large Language Model (LLM)-empowered multi-agent systems extend the cognitive boundaries of individual agents through disciplined collaboration and interaction, while constructing these systems often requires labor-intensive manual designs.
HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation Paper
Abstract
We present HealthGPT, a powerful Medical Large Vision-Language Model (Med-LVLM) that integrates medical visual comprehension and generation capabilities within a unified autoregressive paradigm. Our bootstrapping philosophy is to progressively adapt heterogeneous comprehension and generation knowledge to pre-trained large language models (LLMs). This is achieved through a novel heterogeneous low-rank adaptation (H-LoRA) technique, which is complemented by a tailored hierarchical visual perception approach and a three-stage learning strategy. To effectively learn the HealthGPT, we devise a comprehensive medical domain-specific comprehension and generation dataset called VL-Health. Experimental results demonstrate exceptional performance and scalability of HealthGPT in medical visual unified tasks. Our project can be accessed at https://github.com/DCDmllm/HealthGPT.
Claim
We present HealthGPT, a powerful Medical Large Vision-Language Model (Med-LVLM) that integrates medical visual comprehension and generation capabilities within a unified autoregressive paradigm.
SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering? Paper
Abstract
We introduce SWE-Lancer, a benchmark of over 1,400 freelance software engineering tasks from Upwork, valued at $1 million USD total in real-world payouts. SWE-Lancer encompasses both independent engineering tasks--ranging from $50 bug fixes to $32,000 feature implementations--and managerial tasks, where models choose between technical implementation proposals. Independent tasks are graded with end-to-end tests triple-verified by experienced software engineers, while managerial decisions are assessed against the choices of the original hired engineering managers. We evaluate model performance and find that frontier models are still unable to solve the majority of tasks. To facilitate future research, we open-source a unified Docker image and a public evaluation split, SWE-Lancer Diamond (https://github.com/openai/SWELancer-Benchmark). By mapping model performance to monetary value, we hope SWE-Lancer enables greater research into the economic impact of AI model development.
Claim
We introduce SWE-Lancer, a benchmark of over 1,400 freelance software engineering tasks from Upwork, valued at $1 million USD total in real-world payouts.
Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas Paper
Abstract
Large Vision Language Models (VLMs) have long struggled with spatial reasoning tasks. Surprisingly, even simple spatial reasoning tasks, such as recognizing"under"or"behind"relationships between only two objects, pose significant challenges for current VLMs. In this work, we study the spatial reasoning challenge from the lens of mechanistic interpretability, diving into the model's internal states to examine the interactions between image and text tokens. By tracing attention distribution over the image through out intermediate layers, we observe that successful spatial reasoning correlates strongly with the model's ability to align its attention distribution with actual object locations, particularly differing between familiar and unfamiliar spatial relationships. Motivated by these findings, we propose ADAPTVIS based on inference-time confidence scores to sharpen the attention on highly relevant regions when confident, while smoothing and broadening the attention window to consider a wider context when confidence is lower. This training-free decoding method shows significant improvement (e.g., up to a 50 absolute point improvement) on spatial reasoning benchmarks such as WhatsUp and VSR with negligible cost. We make code and data publicly available for research purposes at https://github.com/shiqichen17/AdaptVis.
Claim
Large Vision Language Models (VLMs) have long struggled with spatial reasoning tasks.
Time-VLM: Exploring Multimodal Vision-Language Models for Augmented Time Series Forecasting Paper
Abstract
Recent advancements in time series forecasting have explored augmenting models with text or vision modalities to improve accuracy. While text provides contextual understanding, it often lacks fine-grained temporal details. Conversely, vision captures intricate temporal patterns but lacks semantic context, limiting the complementary potential of these modalities. To address this, we propose \method, a novel multimodal framework that leverages pre-trained Vision-Language Models (VLMs) to bridge temporal, visual, and textual modalities for enhanced forecasting. Our framework comprises three key components: (1) a Retrieval-Augmented Learner, which extracts enriched temporal features through memory bank interactions; (2) a Vision-Augmented Learner, which encodes time series as informative images; and (3) a Text-Augmented Learner, which generates contextual textual descriptions. These components collaborate with frozen pre-trained VLMs to produce multimodal embeddings, which are then fused with temporal features for final prediction. Extensive experiments demonstrate that Time-VLM achieves superior performance, particularly in few-shot and zero-shot scenarios, thereby establishing a new direction for multimodal time series forecasting. Code is available at https://github.com/CityMind-Lab/ICML25-TimeVLM.
Claim
Recent advancements in time series forecasting have explored augmenting models with text or vision modalities to improve accuracy.
SafeArena: Evaluating the Safety of Autonomous Web Agents Paper
Abstract
LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on a website. To evaluate these risks, we propose SafeArena, the first benchmark to focus on the deliberate misuse of web agents. SafeArena comprises 250 safe and 250 harmful tasks across four websites. We classify the harmful tasks into five harm categories -- misinformation, illegal activity, harassment, cybercrime, and social bias, designed to assess realistic misuses of web agents. We evaluate leading LLM-based web agents, including GPT-4o, Claude-3.5 Sonnet, Qwen-2-VL 72B, and Llama-3.2 90B, on our benchmark. To systematically assess their susceptibility to harmful tasks, we introduce the Agent Risk Assessment framework that categorizes agent behavior across four risk levels. We find agents are surprisingly compliant with malicious requests, with GPT-4o and Qwen-2 completing 34.7% and 27.3% of harmful requests, respectively. Our findings highlight the urgent need for safety alignment procedures for web agents. Our benchmark is available here: https://safearena.github.io
Claim
LLM-based agents are becoming increasingly proficient at solving web-based tasks.
RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing Paper
Abstract
Code auditing is the process of reviewing code with the aim of identifying bugs. Large Language Models (LLMs) have demonstrated promising capabilities for this task without requiring compilation, while also supporting user-friendly customization. However, auditing a code repository with LLMs poses significant challenges: limited context windows and hallucinations can degrade the quality of bug reports, and analyzing large-scale repositories incurs substantial time and token costs, hindering efficiency and scalability. This work introduces an LLM-based agent, RepoAudit, designed to perform autonomous repository-level code auditing. Equipped with agent memory, RepoAudit explores the codebase on demand by analyzing data-flow facts along feasible program paths within individual functions. It further incorporates a validator module to mitigate hallucinations by verifying data-flow facts and checking the satisfiability of path conditions associated with potential bugs, thereby reducing false positives. RepoAudit detects 40 true bugs across 15 real-world benchmark projects with a precision of 78.43%, requiring on average only 0.44 hours and $2.54 per project. Also, it detects 185 new bugs in high-profile projects, among which 174 have been confirmed or fixed. We have open-sourced RepoAudit at https://github.com/PurCL/RepoAudit.
Claim
Code auditing is the process of reviewing code with the aim of identifying bugs.
AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models Paper
Abstract
The emergence of multimodal large language models (MLLMs) advances multimodal emotion recognition (MER) to the next level, from naive discriminative tasks to complex emotion understanding with advanced video understanding abilities and natural language description. However, the current community suffers from a lack of large-scale datasets with intensive, descriptive emotion annotations, as well as a multimodal-centric framework to maximize the potential of MLLMs for emotion understanding. To address this, we establish a new benchmark for MLLM-based emotion understanding with a novel dataset (MER-Caption) and a new model (AffectGPT). Utilizing our model-based crowd-sourcing data collection strategy, we construct the largest descriptive emotion dataset to date (by far), featuring over 2K fine-grained emotion categories across 115K samples. We also introduce the AffectGPT model, designed with pre-fusion operations to enhance multimodal integration. Finally, we present MER-UniBench, a unified benchmark with evaluation metrics tailored for typical MER tasks and the free-form, natural language output style of MLLMs. Extensive experimental results show AffectGPT's robust performance across various MER tasks. We have released both the code and the dataset to advance research and development in emotion understanding: https://github.com/zeroQiaoba/AffectGPT.
Claim
The emergence of multimodal large language models (MLLMs) advances multimodal emotion recognition (MER) to the next level, from naive discriminative tasks to complex emotion understanding with advanced video understanding abilities and natural language description.
R-Bench: Graduate-level Multi-disciplinary Benchmarks for LLM & MLLM Complex Reasoning Evaluation Paper
Abstract
Reasoning stands as a cornerstone of intelligence, enabling the synthesis of existing knowledge to solve complex problems. Despite remarkable progress, existing reasoning benchmarks often fail to rigorously evaluate the nuanced reasoning capabilities required for complex, real-world problemsolving, particularly in multi-disciplinary and multimodal contexts. In this paper, we introduce a graduate-level, multi-disciplinary, EnglishChinese benchmark, dubbed as Reasoning Bench (R-Bench), for assessing the reasoning capability of both language and multimodal models. RBench spans 1,094 questions across 108 subjects for language model evaluation and 665 questions across 83 subjects for multimodal model testing in both English and Chinese. These questions are meticulously curated to ensure rigorous difficulty calibration, subject balance, and crosslinguistic alignment, enabling the assessment to be an Olympiad-level multi-disciplinary benchmark. We evaluate widely used models, including OpenAI o1, GPT-4o, DeepSeek-R1, etc. Experimental results indicate that advanced models perform poorly on complex reasoning, especially multimodal reasoning. Even the top-performing model OpenAI o1 achieves only 53.2% accuracy on our multimodal evaluation. Data and code are made publicly available at here.
Claim
Reasoning stands as a cornerstone of intelligence, enabling the synthesis of existing knowledge to solve complex problems.
MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse Attention Paper
Abstract
The integration of long-context capabilities with visual understanding unlocks unprecedented potential for Vision Language Models (VLMs). However, the quadratic attention complexity during the pre-filling phase remains a significant obstacle to real-world deployment. To overcome this limitation, we introduce MMInference (Multimodality Million tokens Inference), a dynamic sparse attention method that accelerates the prefilling stage for long-context multi-modal inputs. First, our analysis reveals that the temporal and spatial locality of video input leads to a unique sparse pattern, the Grid pattern. Simultaneously, VLMs exhibit markedly different sparse distributions across different modalities. We introduce a permutation-based method to leverage the unique Grid pattern and handle modality boundary issues. By offline search the optimal sparse patterns for each head, MMInference constructs the sparse distribution dynamically based on the input. We also provide optimized GPU kernels for efficient sparse computations. Notably, MMInference integrates seamlessly into existing VLM pipelines without any model modifications or fine-tuning. Experiments on multi-modal benchmarks-including Video QA, Captioning, VisionNIAH, and Mixed-Modality NIAH-with state-of-the-art long-context VLMs (LongVila, LlavaVideo, VideoChat-Flash, Qwen2.5-VL) show that MMInference accelerates the pre-filling stage by up to 8.3x at 1M tokens while maintaining accuracy. Our code is available at https://aka.ms/MMInference.
Claim
The integration of long-context capabilities with visual understanding unlocks unprecedented potential for Vision Language Models (VLMs).
KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search Paper
Abstract
Knowledge Base Question Answering (KBQA) aims to answer natural language questions with a large-scale structured knowledge base (KB). Despite advancements with large language models (LLMs), KBQA still faces challenges in weak KB awareness, imbalance between effectiveness and efficiency, and high reliance on annotated data. To address these challenges, we propose KBQA-o1, a novel agentic KBQA method with Monte Carlo Tree Search (MCTS). It introduces a ReAct-based agent process for stepwise logical form generation with KB environment exploration. Moreover, it employs MCTS, a heuristic search method driven by policy and reward models, to balance agentic exploration's performance and search space. With heuristic exploration, KBQA-o1 generates high-quality annotations for further improvement by incremental fine-tuning. Experimental results show that KBQA-o1 outperforms previous low-resource KBQA methods with limited annotated data, boosting Llama-3.1-8B model's GrailQA F1 performance to 78.5% compared to 48.5% of the previous sota method with GPT-3.5-turbo. Our code is publicly available.
Claim
Knowledge Base Question Answering (KBQA) aims to answer natural language questions with a large-scale structured knowledge base (KB).
Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agents Paper
Abstract
Large-language models (LLMs) and chatbot agents are known to provide wrong outputs at times, and it was recently found that this can never be fully prevented. Hence, uncertainty quantification plays a crucial role, aiming to quantify the level of ambiguity in either one overall number or two numbers for aleatoric and epistemic uncertainty. This position paper argues that this traditional dichotomy of uncertainties is too limited for the open and interactive setup that LLM agents operate in when communicating with a user, and that we need to research avenues that enrich uncertainties in this novel scenario. We review the literature and find that popular definitions of aleatoric and epistemic uncertainties directly contradict each other and lose their meaning in interactive LLM agent settings. Hence, we propose three novel research directions that focus on uncertainties in such human-computer interactions: Underspecification uncertainties, for when users do not provide all information or define the exact task at the first go, interactive learning, to ask follow-up questions and reduce the uncertainty about the current context, and output uncertainties, to utilize the rich language and speech space to express uncertainties as more than mere numbers. We expect that these new ways of dealing with and communicating uncertainties will lead to LLM agent interactions that are more transparent, trustworthy, and intuitive.
Claim
Large-language models (LLMs) and chatbot agents are known to provide wrong outputs at times, and it was recently found that this can never be fully prevented.
Multi-Turn Code Generation Through Single-Step Rewards Paper
Abstract
We address the problem of code generation from multi-turn execution feedback. Existing methods either generate code without feedback or use complex, hierarchical reinforcement learning to optimize multi-turn rewards. We propose a simple yet scalable approach, \(\mu\)Code, that solves multi-turn code generation using only single-step rewards. Our key insight is that code generation is a one-step recoverable MDP, where the correct code can be recovered from any intermediate code state in a single turn. \(\mu\)Code iteratively trains both a generator to provide code solutions conditioned on multi-turn execution feedback and a verifier to score the newly generated code. Experimental evaluations show that our approach achieves significant improvements over the state-of-the-art baselines. We provide analysis of the design choices of the reward models and policy, and show the efficacy of \(\mu\)Code at utilizing the execution feedback. Our code is available at https://github.com/portal-cornell/muCode.
Claim
We address the problem of code generation from multi-turn execution feedback.
Unlocking the Capabilities of Large Vision-Language Models for Generalizable and Explainable Deepfake Detection Paper
Abstract
Current Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in understanding multimodal data, but their potential remains underexplored for deepfake detection due to the misalignment of their knowledge and forensics patterns. To this end, we present a novel framework that unlocks LVLMs' potential capabilities for deepfake detection. Our framework includes a Knowledge-guided Forgery Detector (KFD), a Forgery Prompt Learner (FPL), and a Large Language Model (LLM). The KFD is used to calculate correlations between image features and pristine/deepfake image description embeddings, enabling forgery classification and localization. The outputs of the KFD are subsequently processed by the Forgery Prompt Learner to construct fine-grained forgery prompt embeddings. These embeddings, along with visual and question prompt embeddings, are fed into the LLM to generate textual detection responses. Extensive experiments on multiple benchmarks, including FF++, CDF2, DFD, DFDCP, DFDC, and DF40, demonstrate that our scheme surpasses state-of-the-art methods in generalization performance, while also supporting multi-turn dialogue capabilities.
Claim
Current Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in understanding multimodal data, but their potential remains underexplored for deepfake detection due to the misalignment of their knowledge and forensics patterns.
Self-Improving Language Models for Evolutionary Program Synthesis: A Case Study on ARC-AGI Paper
Abstract
Many program synthesis tasks prove too challenging for even state-of-the-art language models to solve in single attempts. Search-based evolutionary methods offer a promising alternative by exploring solution spaces iteratively, but their effectiveness remain limited by the fixed capabilities of the underlying generative model. We propose SOAR, a method that learns program synthesis by integrating language models into a self-improving evolutionary loop. SOAR alternates between (1) an evolutionary search that uses an LLM to sample and refine candidate solutions, and (2) a hindsight learning phase that converts search attempts into valid problem-solution pairs used to fine-tune the LLM's sampling and refinement capabilities -- enabling increasingly effective search in subsequent iterations. On the challenging ARC-AGI benchmark, SOAR achieves significant performance gains across model scales and iterations, leveraging positive transfer between the sampling and refinement finetuning tasks. These improvements carry over to test-time adaptation, enabling SOAR to solve 52% of the public test set. Our code is open-sourced at: https://github.com/flowersteam/SOAR
Claim
Many program synthesis tasks prove too challenging for even state-of-the-art language models to solve in single attempts.
Sparse Autoencoders for Hypothesis Generation Paper
Abstract
We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e.g., headlines) and a target variable (e.g., clicks). HypotheSAEs has three steps: (1) train a sparse autoencoder on text embeddings to produce interpretable features describing the data distribution, (2) select features that predict the target variable, and (3) generate a natural language interpretation of each feature (e.g.,"mentions being surprised or shocked") using an LLM. Each interpretation serves as a hypothesis about what predicts the target variable. Compared to baselines, our method better identifies reference hypotheses on synthetic datasets (at least +0.06 in F1) and produces more predictive hypotheses on real datasets ( twice as many significant findings), despite requiring 1-2 orders of magnitude less compute than recent LLM-based methods. HypotheSAEs also produces novel discoveries on two well-studied tasks: explaining partisan differences in Congressional speeches and identifying drivers of engagement with online headlines.
Claim
We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e.g., headlines) and a target variable (e.g., clicks).