ICLR 2025 论文列表

Recent works have increasingly focused on learning decentralized policies for agents as a solution to the scalability challenges in Multi-Agent Reinforcement Learning (MARL), where agents typically share the parameters of a policy network to make action decisions. However, this parameter sharing can impede efficient exploration, as it may lead to similar behaviors among agents. Different from previous mutual information-based methods that promote multi-agent diversity, we introduce a novel multi-agent exploration method called Trajectory Entropy Exploration (TEE). Our method employs a particle-based entropy estimator to maximize the entropy of different agents' trajectories in a contrastive trajectory representation space, resulting in diverse trajectories and efficient exploration. This entropy estimator avoids challenging density modeling and scales effectively in high-dimensional multi-agent settings. We integrate our method with MARL algorithms by deploying an intrinsic reward for each agent to encourage entropy maximization. To validate the effectiveness of our method, we test our method in challenging multi-agent tasks from several MARL benchmarks. The results demonstrate that our method consistently outperforms existing state-of-the-art methods.

As language models (LMs) are used to build autonomous agents in real environments, ensuring their adversarial robustness becomes a critical challenge. Unlike chatbots, agents are compound systems with multiple components taking actions, which existing LMs safety evaluations do not adequately address. To bridge this gap, we manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena, a real environment for web agents. To systematically examine the robustness of agents, we propose the Agent Robustness Evaluation (ARE) framework. ARE views the agent as a graph showing the flow of intermediate outputs between components and decomposes robustness as the flow of adversarial information on the graph. We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search. With imperceptible perturbations to a single image (less than 5% of total web page pixels), an attacker can hijack these agents to execute targeted adversarial goals with success rates up to 67%. We also use ARE to rigorously evaluate how the robustness changes as new components are added. We find that inference-time compute that typically improves benign performance can open up new vulnerabilities and harm robustness. An attacker can compromise the evaluator used by the reflexion agent and the value function of the tree search agent, which increases the attack success relatively by 15% and 20%. Our data and code for attacks, defenses, and evaluation are at https://github.com/ChenWu98/agent-attack

In this paper, we investigate the problem of embodied multi-agent cooperation, where decentralized agents must cooperate given only egocentric views of the world. To effectively plan in this setting, in contrast to learning world dynamics in a single-agent scenario, we must simulate world dynamics conditioned on an arbitrary number of agents' actions given only partial egocentric visual observations of the world. To address this issue of partial observability, we first train generative models to estimate the overall world state given partial egocentric observations. To enable accurate simulation of multiple sets of actions on this world state, we then propose to learn a compositional world model for multi-agent cooperation by factorizing the naturally composable joint actions of multiple agents and compositionally generating the video conditioned on the world state. By leveraging this compositional world model, in combination with Vision Language Models to infer the actions of other agents, we can use a tree search procedure to integrate these modules and facilitate online cooperative planning. We evaluate our methods on three challenging benchmarks with 2-4 agents. The results show our compositional world model is effective and the framework enables the embodied agents to cooperate efficiently with different agents across various tasks and an arbitrary number of agents, showing the promising future of our proposed methods. More videos can be found at https://umass-embodied-agi.github.io/COMBO

An important challenge in multi-agent reinforcement learning is partial observability, where agents cannot access the global state of the environment during execution and can only receive observations within their field of view. To address this issue, previous works typically use the dimensional-wise state, which is obtained by applying MLP or dimensional-based attention on the global state, for decision-making during training and relying on a reconstructed dimensional-wise state during execution. However, dimensional-wise states tend to divert agent attention to specific features, neglecting potential dependencies between agents, making it difficult to make optimal decisions. Moreover, the inconsistency between the states used in training and execution further increases additional errors. To resolve these issues, we propose a method called Reconstruction-Guided Policy (RGP) to reconstruct the agent-wise state, which represents the information of inter-agent relationships, as input for decision-making during both training and execution. This not only preserves the potential dependencies between agents but also ensures consistency between the states used in training and execution. We conducted extensive experiments on both discrete and continuous action environments to evaluate RGP, and the results demonstrates its superior effectiveness. Our code is public in https://anonymous.4open.science/r/RGP-9F79

Despite the popularity of multi-agent reinforcement learning (RL) in simulated and two-player applications, its success in messy real-world applications has been limited. A key challenge lies in its generalizability across problem variations, a common necessity for many real-world problems. Contextual reinforcement learning (CRL) formalizes learning policies that generalize across problem variations. However, the lack of standardized benchmarks for multi-agent CRL has hindered progress in the field. Such benchmarks are desired to be based on real-world applications to naturally capture the many open challenges of real-world problems that affect generalization. To bridge this gap, we propose IntersectionZoo, a comprehensive benchmark suite for multi-agent CRL through the real-world application of cooperative eco-driving in urban road networks. The task of cooperative eco-driving is to control a fleet of vehicles to reduce fleet-level vehicular emissions. By grounding IntersectionZoo in a real-world application, we naturally capture real-world problem characteristics, such as partial observability and multiple competing objectives. IntersectionZoo is built on data-informed simulations of 16,334 signalized intersections derived from 10 major US cities, modeled in an open-source industry-grade microscopic traffic simulator. By modeling factors affecting vehicular exhaust emissions (e.g., temperature, road conditions, travel demand), IntersectionZoo provides one million data-driven traffic scenarios. Using these traffic scenarios, we benchmark popular multi-agent RL and human-like driving algorithms and demonstrate that the popular multi-agent RL algorithms struggle to generalize in CRL settings.

Real-world enterprise text-to-SQL workflows often involve complex cloud or local data across various database systems, multiple SQL queries in various dialects, and diverse operations from data transformation to analytics. We introduce Spider 2.0, an evaluation framework comprising $632$ real-world text-to-SQL workflow problems derived from enterprise-level database use cases. The databases in Spider 2.0 are sourced from real data applications, often containing over 1,000 columns and stored in local or cloud database systems such as BigQuery and Snowflake. We show that solving problems in Spider 2.0 frequently requires understanding and searching through database metadata, dialect documentation, and even project-level codebases. This challenge calls for models to interact with complex SQL workflow environments, process extremely long contexts, perform intricate reasoning, and generate multiple SQL queries with diverse operations, often exceeding $100$ lines, which goes far beyond traditional text-to-SQL challenges. Our evaluations indicate that based on o1-preview, our code agent framework successfully solves only 21.3\% of the tasks, compared with 91.2\% on Spider 1.0 and 73.0\% on BIRD. Our results on Spider 2.0 show that while language models have demonstrated remarkable performance in code generation --- especially in prior text-to-SQL benchmarks --- they require significant improvement in order to achieve adequate performance for real-world enterprise usage. Progress on Spider 2.0 represents crucial steps towards developing intelligent, autonomous, code agents for real-world enterprise settings. Our code, baseline models, and data are available at [spider2-sql.github.io](spider2-sql.github.io) .

As large language models (LLMs) advance, their inability to autonomously execute tasks by directly interacting with external tools remains a critical limitation. Traditional methods rely on inputting tool descriptions as context, which is constrained by context length and requires separate, often inefficient, retrieval mechanisms. We introduce ToolGen, a paradigm shift that integrates tool knowledge directly into the LLM’s parameters by representing each tool as a unique token. This enables the LLM to generate tool calls and arguments as part of its next token prediction capabilities, seamlessly blending tool invocation with language generation. Our framework allows the LLM to access and utilize a vast amount of tools with no additional retrieval step, significantly enhancing both performance and scalability. Experimental results with over 47,000 tools show that ToolGen not only achieves superior results in both tool retrieval and autonomous task completion but also sets the stage for a new era of AI agents that can adapt to tools across diverse domains. By fundamentally transforming tool retrieval into a generative process, ToolGen paves the way for more versatile, efficient, and autonomous AI systems. ToolGen enables end-to-end tool learning and opens opportunities for integration with other advanced techniques such as chain-of-thought and reinforcement learning, thereby expanding the practical capabilities of LLMs

Scientific discovery contributes largely to the prosperity of human society, and recent progress shows that LLMs could potentially catalyst the process. However, it is still unclear whether LLMs can discover novel and valid hypotheses in chemistry. In this work, we investigate this main research question: whether LLMs can automatically discover novel and valid chemistry research hypotheses, given only a research question? With extensive discussions with chemistry experts, we adopt the assumption that a majority of chemistry hypotheses can be resulted from a research background question and several inspirations. With this key insight, we break the main question into three smaller fundamental questions. In brief, they are: (1) given a background question, whether LLMs can retrieve good inspirations; (2) with background and inspirations, whether LLMs can lead to hypothesis; and (3) whether LLMs can identify good hypotheses to rank them higher. To investigate these questions, we construct a benchmark consisting of 51 chemistry papers published in Nature or a similar level in 2024 (all papers are only available online since 2024). Every paper is divided by chemistry PhD students into three components: background, inspirations, and hypothesis. The goal is to rediscover the hypothesis given only the background and a large chemistry literature corpus consisting the ground truth inspiration papers, with LLMs trained with data up to 2023. We also develop an LLM-based multi-agent framework that leverages the assumption, consisting of three stages reflecting the more smaller questions. The proposed method can rediscover many hypotheses with very high similarity with the ground truth ones, covering the main innovations.

High-quality preference data is essential for aligning foundation models with human values through preference learning. However, manual annotation of such data is often time-consuming and costly. Recent methods often adopt a self-rewarding approach, where the target model generates and annotates its own preference data, but this can lead to inaccuracies since the reward model shares weights with the target model, thereby amplifying inherent biases. To address these issues, we propose Anyprefer, a framework designed to synthesize high-quality preference data for aligning the target model. Anyprefer frames the data synthesis process as a cooperative two-player Markov Game, where the target model and the judge model collaborate together. Here, a series of external tools are introduced to assist the judge model in accurately rewarding the target model’s responses, mitigating biases in the rewarding process. In addition, a feedback mechanism is introduced to optimize prompts for both models, enhancing collaboration and improving data quality. The synthesized data is compiled into a new preference dataset, Anyprefer-V1, consisting of 58K high-quality preference pairs. Extensive experiments show that Anyprefer significantly improves model alignment performance across four main applications, covering 21 datasets, achieving average improvements of 18.55% in five natural language generation datasets, 3.66% in nine vision-language understanding datasets, 30.05% in three medical image analysis datasets, and 16.00% in four visuo-motor control tasks.

Graph neural networks (GNNs) appear to be powerful tools to learn state representations for agents in distributed, decentralized multi-agent systems, but generate catastrophically incorrect predictions when nodes update asynchronously during inference. This failure under asynchrony effectively excludes these architectures from many potential applications where synchrony is difficult or impossible to enforce, e.g., robotic swarms or sensor networks. In this work we identify ''implicitly-defined'' GNNs as a class of architectures which is provably robust to asynchronous ''hogwild'' inference, adapting convergence guarantees from work in asynchronous and distributed optimization. We then propose a novel implicitly-defined GNN architecture, which we call an energy GNN. We show that this architecture outperforms other GNNs from this class on a variety of synthetic tasks inspired by multi-agent systems.

Large language models (LLMs) and large multimodal models (LMMs) have shown great potential in automating complex tasks like web browsing and gaming. However, their ability to generalize across diverse applications remains limited, hindering broader utility. To address this challenge, we present OSCAR: Operating System Control via state-Aware reasoning and Re-planning. OSCAR is a generalist agent designed to autonomously navigate and interact with various desktop and mobile applications through standardized controls, such as mouse and keyboard inputs, while processing screen images to fulfill user commands. OSCAR translates human instructions into executable Python code, enabling precise control over graphical user interfaces (GUIs). To enhance stability and adaptability, OSCAR operates as a state machine, equipped with error-handling mechanisms and dynamic task re-planning, allowing it to efficiently adjust to real-time feedback and exceptions. We demonstrate OSCAR’s effectiveness through extensive experiments on diverse benchmarks across desktop and mobile platforms, where it transforms complex workflows into simple natural language commands, significantly boosting user productivity. Our code will be open-source upon publication.

Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical security vulnerabilities. However, the existing literature does not comprehensively evaluate attacks and defenses against LLM-based agents. To address this, we introduce Agent Security Bench (ASB), a comprehensive framework designed to formalize, benchmark, and evaluate the attacks and defenses of LLM-based agents, including 10 scenarios (e.g., e-commerce, autonomous driving, finance), 10 agents targeting the scenarios, over 400 tools, 27 different types of attack/defense methods, and 7 evaluation metrics. Based on ASB, we benchmark 10 prompt injection attacks, a memory poisoning attack, a novel Plan-of-Thought backdoor attack, 4 mixed attacks, and 11 corresponding defenses across 13 LLM backbones. Our benchmark results reveal critical vulnerabilities in different stages of agent operation, including system prompt, user prompt handling, tool usage, and memory retrieval, with the highest average attack success rate of 84.30\%, but limited effectiveness shown in current defenses, unveiling important works to be done in terms of agent security for the community. We also introduce a new metric to evaluate the agents' capability to balance utility and security. Our code can be found at https://github.com/agiresearch/ASB.

As the mainstream approach, LLMs have been widely applied and researched in TableQA tasks. Currently, the core of LLM-based TableQA methods typically include three phases: question decomposition, sub-question TableQA reasoning, and answer verification. However, several challenges remain in this process: i) Sub-questions generated by these methods often exhibit significant gaps with the original question due to critical information overlooked during the LLM's direct decomposition; ii) Verification of answers is typically challenging because LLMs tend to generate optimal responses during self-correct. To address these challenges, we propose a Triple-Inspired Decomposition and vErification (TIDE) strategy, which leverages the structural properties of triples to assist in decomposition and verification in TableQA. The inherent structure of triples (head entity, relation, tail entity) requires the LLM to extract as many entities and relations from the question as possible. Unlike direct decomposition methods that may overlook key information, our transformed sub-questions using triples encompass more critical details. Additionally, this explicit structure facilitates verification. By comparing the triples derived from the answers with those from the question decomposition, we can achieve easier and more straightforward validation than when relying on the LLM's self-correct tendencies. By employing triples alongside established LLM modes, Direct Prompting and Agent modes, TIDE achieves state-of-the-art performance across multiple TableQA datasets, demonstrating the effectiveness of our method.

Vehicle trajectory prediction is a crucial aspect of autonomous driving, which requires extensive trajectory data to train prediction models to understand the complex, varied, and unpredictable patterns of vehicular interactions. However, acquiring real-world data is expensive, so we advocate using Large Language Models (LLMs) to generate abundant and realistic trajectories of interacting vehicles efficiently. These models rely on textual descriptions of vehicle-to-vehicle interactions on a map to produce the trajectories. We introduce Trajectory-LLM (Traj-LLM), a new approach that takes brief descriptions of vehicular interactions as input and generates corresponding trajectories. Unlike language-based approaches that translate text directly to trajectories, Traj-LLM uses reasonable driving behaviors to align the vehicle trajectories with the text. This results in an "interaction-behavior-trajectory" translation process. We have also created a new dataset, Language-to-Trajectory (L2T), which includes 240K textual descriptions of vehicle interactions and behaviors, each paired with corresponding map topologies and vehicle trajectory segments. By leveraging the L2T dataset, Traj-LLM can adapt interactive trajectories to diverse map topologies. Furthermore, Traj-LLM generates additional data that enhances downstream prediction models, leading to consistent performance improvements across public benchmarks. The source code is released at https://github.com/TJU-IDVLab/Traj-LLM.

Rating-based human evaluation has become an essential tool to accurately evaluate the impressive performance of large language models (LLMs). However, current rating systems suffer from several important limitations: first, they fail to account for biases that significantly influence evaluation results, second, they require large and expensive preference datasets to obtain accurate ratings, and third, they do not facilitate meaningful comparisons of model ratings across different tasks. To address these issues, we introduce Polyrating, an expressive and flexible rating system based on maximum a posteriori estimation that enables a more nuanced and thorough analysis of model performance at lower costs. Polyrating can detect and quantify biases affecting human preferences, ensuring fairer model comparisons. Further, Polyrating can reduce the cost of human evaluations by up to $41$% for new models and up to $77$% for new tasks by leveraging existing benchmark scores. Lastly, Polyrating enables direct comparisons of ratings across different tasks, providing a comprehensive understanding of an LLMs' strengths, weaknesses, and relative performance across different applications.

An ideal multimodal agent should be aware of the quality of its input modalities. Recent advances have enabled large language models (LLMs) to incorporate auditory systems for handling various speech-related tasks. However, most audio LLMs remain unaware of the quality of the speech they process. This limitation arises because speech quality evaluation is typically excluded from multi-task training due to the lack of suitable datasets. To address this, we introduce the first natural language-based speech evaluation corpus, generated from authentic human ratings. In addition to the overall Mean Opinion Score (MOS), this corpus offers detailed analysis across multiple dimensions and identifies causes of quality degradation. It also enables descriptive comparisons between two speech samples (A/B tests) with human-like judgment. Leveraging this corpus, we propose an alignment approach with LLM distillation (ALLD) to guide the audio LLM in extracting relevant information from raw speech and generating meaningful responses. Experimental results demonstrate that ALLD outperforms the previous state-of-the-art regression model in MOS prediction, with a mean square error of 0.17 and an A/B test accuracy of 98.6%. Additionally, the generated responses achieve BLEU scores of 25.8 and 30.2 on two tasks, surpassing the capabilities of task-specific models. This work advances the comprehensive perception of speech signals by audio LLMs, contributing to the development of real-world auditory and sensory intelligent agents.

Large Language Models (LLMs) have showcased remarkable reasoning capabilities in various domains, yet face challenges in complex embodied tasks due to the need for a coherent long-term policy and context-sensitive environmental understanding. Previous work performed LLM refinement relying on outcome-supervised feedback, which can be costly and ineffective. In this work, we introduce a novel framework, Discriminator-Guided Action Optimization (DGAP), for facilitating the optimization of LLM action plans via step-wise signals. Specifically, we employ a limited set of demonstrations to enable the discriminator to learn a score function, which assesses the alignment between LLM-generated actions and the underlying optimal ones at every step. Based on the discriminator, LLMs are prompted to generate actions that maximize the score, utilizing historical action-score pair trajectories as guidance. Under mild conditions, DGAP resembles critic-regularized optimization and has been demonstrated to achieve a stronger policy than the LLM planner. In experiments across different LLMs (GPT-4, Llama3-70B) in ScienceWorld and VirtualHome, our method achieves superior performance and better efficiency than previous methods.

We present a benchmark for Planning And Reasoning Tasks in humaN-Robot collaboration (PARTNR) designed to study human-robot coordination in household activities. PARTNR tasks exhibit characteristics of everyday tasks, such as spatial, temporal, and heterogeneous agent capability constraints. We employ a semi-automated task generation pipeline using Large Language Models (LLMs), incorporating simulation-in-the-loop for the grounding and verification. PARTNR stands as the largest benchmark of its kind, comprising 100,000 natural language tasks, spanning 60 houses and 5,819 unique objects. We analyze state-of-the-art LLMs on PARTNR tasks, across the axes of planning, perception and skill execution. The analysis reveals significant limitations in SoTA models, such as poor coordination and failures in task tracking and recovery from errors. When LLMs are paired with 'real' humans, they require 1.5x as many steps as two humans collaborating and 1.1x more steps than a single human, underscoring the potential for improvement in these models. We further show that fine-tuning smaller LLMs with planning data can achieve performance on par with models 9 times larger, while being 8.6x faster at inference. Overall, PARTNR highlights significant challenges facing collaborative embodied agents and aims to drive research in this direction.

With the growing capabilities of large language models (LLMs), they are increasingly applied in areas like intelligent customer service, code generation, and knowledge management. Natural language (NL) prompts act as the ``APIs'' for human-LLM interaction. To improve prompt quality, best practices for prompt engineering (PE) have been developed, including writing guidelines and templates. Building on this, we propose Controlled NL for Prompt (CNL-P), which not only incorporates PE best practices but also draws on key principles from software engineering (SE). CNL-P introduces precise grammar structures and strict semantic norms, further eliminating NL's ambiguity, allowing for a declarative but structured and accurate expression of user intent. This helps LLMs better interpret and execute the prompts, leading to more consistent and higher-quality outputs. We also introduce an NL2CNL-P conversion tool based on LLMs, enabling users to write prompts in NL, which are then transformed into CNL-P format, thus lowering the learning curve of CNL-P. In particular, we develop a linting tool that checks CNL-P prompts for syntactic and semantic accuracy, applying static analysis techniques to NL for the first time. Extensive experiments demonstrate that CNL-P enhances the quality of LLM responses through the novel and organic synergy of PE and SE. We believe that CNL-P can bridge the gap between emerging PE and traditional SE, laying the foundation for a new programming paradigm centered around NL. To further demonstrate the effectiveness of CNL-P, we develop the AI-native CNL-P IDE, UGAiForge that leverages CNL-P to enable users to Think, Describe, and Build with AI and for AI. For detailed information, please refer https://ugaiforge.ai.