论文检索

Qingwen Yang, Feiyu Qu, Tiezheng Guo, Yanyi Liu, Yingyou Wen

LLM-based multi-agent systems have demonstrated significant capabilities across diverse domains. However, the task performance and efficiency are fundamentally constrained by their collaboration strategies. Prevailing approaches rely on static topologies and centralized global planning, a paradigm that limits their scalability and adaptability in open, decentralized networks. Effective collaboration planning in distributed systems using only local information thus remains a formidable challenge. To address this, we propose BiRouter, a novel dual-criteria routing method for Self-Organizing Multi-Agent Systems (SO-MAS). This method enables each agent to autonomously execute "next-hop" task routing at runtime, relying solely on local information. Its core decision-making mechanism is predicated on balancing two metrics: (1) the ImpScore, which evaluates a candidate agent's long-term importance to the overall goal, and (2) the GapScore, which assesses its contextual continuity for the current task state. Furthermore, we introduce a dynamically updated reputation mechanism to bolster system robustness in untrustworthy environments and have developed a large-scale, cross-domain dataset, comprising thousands of annotated task-routing paths, to enhance the model's generalization. Extensive experiments demonstrate that BiRouter achieves superior performance and token efficiency over existing baselines, while maintaining strong robustness and effectiveness in information-limited, decentralized, and untrustworthy settings.

Liming Yang, Junyu Luo, Xuanzhe Liu, Yiling Lou, Zhenpeng Chen

Large language model (LLM)-based multi-agent systems have emerged as a powerful paradigm for enabling autonomous agents to solve complex tasks. As these systems scale in complexity, cost becomes an important consideration for practical deployment. However, existing work rarely addresses how to structure multi-agent systems under explicit budget constraints. In this paper, we propose BAMAS, a novel approach for building multi-agent systems with budget awareness. BAMAS first selects an optimal set of LLMs by formulating and solving an Integer Linear Programming problem that balances performance and cost. It then determines how these LLMs should collaborate by leveraging a reinforcement learning-based method to select the interaction topology. Finally, the system is instantiated and executed based on the selected agents and their collaboration topology. We evaluate BAMAS on three representative tasks and compare it with state-of-the-art agent construction methods. Results show that BAMAS achieves comparable performance while reducing cost by up to 86%.

Cheng Yang, Hui Jin, Xinlei Yu, Zhipeng Wang, Yaoqun Liu, Fenglei Fan, Dajiang Lei, Gangyong Jia, Changmiao Wang, Ruiquan Ge

Diagnosing lung cancer typically involves physicians identifying lung nodules in Computed tomography (CT) scans and generating diagnostic reports based on their morphological features and medical expertise. Although advancements have been made in using multimodal large language models for analyzing lung CT scans, challenges remain in accurately describing nodule morphology and incorporating medical expertise. These limitations affect the reliability and effectiveness of these models in clinical settings. Collaborative multi-agent systems offer a promising strategy for achieving a balance between generality and precision in medical applications, yet their potential in pathology has not been thoroughly explored. To bridge these gaps, we introduce LungNoduleAgent, an innovative collaborative multi-agent system specifically designed for analyzing lung CT scans. LungNoduleAgent streamlines the diagnostic process into sequential components, improving precision in describing nodules and grading malignancy through three primary modules. The first module, the Nodule Spotter, coordinates clinical detection models to accurately identify nodules. The second module, the Radiologist, integrates localized image description techniques to produce comprehensive CT reports. Finally, the Doctor Agent System performs malignancy reasoning by using images and CT reports, supported by a pathology knowledge base and a multi-agent system framework. Extensive testing on two private datasets and the public LIDC-IDRI dataset indicates that LungNoduleAgent surpasses mainstream vision-language models, agent systems, and advanced expert models such as GPT-4o, Claude 3.7 Sonnet, LLaMA-3.2 Vision, Qwen2.5-VL, Med-R1, MedGemma, MedAgent-Pro, MedAgents, MDAgent and LLaVA-Med. These results highlight the importance of region-level semantic alignment and multi-agent collaboration in diagnosing nodules. LungNoduleAgent stands out as a promising foundational tool for supporting clinical analyses of lung nodules.

Bingyu Yan, Xiaoming Zhang, Ziyi Zhou, Chaozhuo Li, Ruilin Zeng, Yirui Qi, Tianbo Wang, Litian Zhang

Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting LLM-MAS either compromise agent internals or rely on direct and overt persuasion, which limit their effectiveness, adaptability, and stealthiness. In this paper, we propose MAST, a Multi-round Adaptive Stealthy Tampering framework designed to exploit communication vulnerabilities within the system. MAST integrates Monte Carlo Tree Search with Direct Preference Optimization to train an attack policy model that adaptively generates effective multi-round tampering strategies. Furthermore, to preserve stealthiness, we impose dual semantic and embedding similarity constraints during the tampering process. Comprehensive experiments across diverse tasks, communication architectures, and LLMs demonstrate that MAST consistently achieves high attack success rates while significantly enhancing stealthiness compared to baselines. These findings highlight the effectiveness, stealthiness, and adaptability of MAST, underscoring the need for robust communication safeguards in LLM-MAS.

Yuan Xue, Xiaoyu Lu, Yunfei Bai, Yunan Liu, Hoiyi Ng

Understanding the behavior and logical structure of complex algorithms is a fundamental challenge in industrial systems. Recent advancements in large language models (LLMs) have demonstrated remarkable code understanding capabilities. However, their potential for reverse engineering algorithms into interpretable causal structures remains unexplored. In this work, we develop a multi-agent framework, RECoRD, that leverages LLMs to Reverse Engineering Codebase to Causal Relational Diagram. RECoRD uses reinforcement fine-tuning (RFT) to enhance the reasoning accuracy of the relation extraction agent. Fine-tuning on expert-curated causal graphs allows smaller specialized models to outperform larger foundation models on domain-specific tasks. Experiments on three real-world use cases - News Vendor, MiniSCOT, and Black-Scholes - demonstrate the effectiveness of our approach. The RFT-trained models significantly outperformed their foundation counterparts, improving F1 score from 0.69 to 0.97 on MiniSCOT. RECoRD also exhibited strong generalization, with models fine-tuned on one use case improving performance on others. We further show how the extracted causal graphs can be leveraged to build a deep-dive assistant that reasons like domain experts, enabling rapid root cause analysis in complex software systems. By automating the construction of interpretable causal models from code, RECoRD has wide-ranging applications in areas such as software debugging, operational optimization, and risk management.

Yihan Xia, Taotao Wang, Shengli Zhang, Zhangyuhua Weng, Bin Cao, Soung Chang Liew

Recent advances in LLM-based multi-agent systems have demonstrated remarkable capabilities in complex decision-making scenarios such as financial trading and software engineering. However, evaluating each individual agent’s effectiveness and online optimization of underperforming agents remain open challenges. To address these issues, we present HiveMind, a self-adaptive framework designed to optimize LLM multi-agent collaboration through contribution analysis. At its core, HiveMind introduces Contribution-Guided Online Prompt Optimization (CG-OPO), which autonomously refines agent prompts based on their quantified contributions. We first propose the Shapley value as a grounded metric to quantify each agent's contribution, thereby identifying underperforming agents in a principled manner for automated prompt refinement. To overcome the computational complexity of the classical Shapley value, we present DAG-Shapley, a novel and efficient attribution algorithm for Directed Acyclic Graph (DAG)-structured multi-agent workflows that leverages the inherent DAG structure of the agent workflow to axiomatically prune non-viable coalitions. By hierarchically reusing intermediate outputs of agents in the DAG, our method further reduces redundant computations, and achieving substantial cost savings without compromising the theoretical guarantees of Shapley values. Evaluated in a multi-agent stock-trading scenario, HiveMind achieves superior performance compared to static baselines. Notably, DAG-Shapley reduces LLM calls by over 80 percent while maintaining attribution accuracy comparable to full Shapley values, establishing a new standard for efficient credit assignment and enabling scalable, real-world optimization of multi-agent collaboration.

Lixiu Wu, Yuanrong Tang, Qisen Pan, Xianyang Zhan, Yuchen Han, Lanxi Xiao, Tianhong Wang, Chen Zhong, Jiangtao Gong

Due to privacy concerns, open dialogue datasets for mental health are primarily generated through human or AI synthesis methods. However, the inherent implicit nature of psychological processes, particularly those of clients, poses challenges to the authenticity and diversity of synthetic data. In this paper, we propose ECAs (short for Embodied Conversational Agents), a framework for embodied agent simulation based on Large Language Models (LLMs) that incorporates multiple psychological theoretical principles. Using simulation, we expand real counseling case data into a nuanced embodied cognitive memory space and generate dialogue data based on high-frequency counseling questions. We validated our framework using the D4 dataset. First, we created a public ECAs dataset through batch simulations based on D4. Licensed counselors evaluated our method, demonstrating that it significantly outperforms baselines in simulation authenticity and necessity. Additionally, two LLM-based automated evaluation methods were employed to confirm the higher quality of the generated dialogues compared to the baselines.

Hao Wu, Shoucheng Song, Chang Yao, Sheng Han, Huaiyu Wan, Youfang Lin, Kai Lv

In multi-agent systems, explicit cognition of teammates' decision logic serves as a critical factor in facilitating coordination. Communication (i.e., "Tell") can assist in the cognitive development process by information dissemination, yet it is inevitably subject to real-world constraints such as noise, latency, and attacks. Therefore, building the understanding of teammates' decisions without communication remains challenging. To address this, we propose a novel non-communication MARL framework that realizes the construction of cognition through local observation-based modeling (i.e., "Think"). Our framework enables agents to model teammates' active inference process. At first, the proposed method produces three teammate portraits: perception-belief-action. Specifically, we model the teammate's decision process as follows: 1) Perception: observing environments; 2) Belief: forming beliefs; 3) Action: making decisions. Then, we selectively integrate the belief portrait into the decision process based on the accuracy and relevance of the perception portrait. This enables the selection of cooperative teammates and facilitates effective collaboration. Extensive experiments on the SMAC, SMACv2, MPE, and GRF benchmarks demonstrate the superior performance of our method.

Cuiling Wu, Yaozhong Gan, Junliang Xing, Ying Fu

We propose Multi-Agent Reflective Policy Optimization MARPO to alleviate the issue of sample inefficiency in multi-agent reinforcement learning. MARPO consists of two key components: a reflection mechanism that leverages subsequent trajectories to enhance sample efficiency, and an asymmetric clipping mechanism that is derived from the KL divergence and dynamically adjusts the clipping range to improve training stability. We evaluate MARPO in classic multi-agent environments, where it consistently outperforms other methods.

Quanmin Wei, Penglin Dai, Wei Li, Bingyi Liu, Xiao Wu

Precise environmental perception is critical for the reliability of autonomous driving systems. While collaborative perception mitigates the limitations of single-agent perception through information sharing, it encounters a fundamental communication-performance trade-off. Existing communication-efficient approaches typically assume MB-level data transmission per collaboration, which may fail due to practical network constraints. To address these issues, we propose InfoCom, an information-aware framework establishing the pioneering theoretical foundation for communication-efficient collaborative perception via extended Information Bottleneck principles. Departing from mainstream feature manipulation, InfoCom introduces a novel information purification paradigm that theoretically optimizes the extraction of minimal sufficient task-critical information under Information Bottleneck constraints. Its core innovations include: i) An Information-Aware Encoding condensing features into minimal messages while preserving perception-relevant information; ii) A Sparse Mask Generation identifying spatial cues with negligible communication cost; and iii) A Multi-Scale Decoding that progressively recovers perceptual information through mask-guided mechanisms rather than simple feature reconstruction. Comprehensive experiments across multiple datasets demonstrate that InfoCom achieves near-lossless perception while reducing communication overhead from megabyte to kilobyte-scale, representing 440-fold and 90-fold reductions per agent compared to Where2comm and ERMVP, respectively.

Pengyuan Wei, Giorgos Christopoulos, Zhouyang Shen, Jincheng Wang, Joshua Mukherjee, Ryuji Hirayama, Sriram Subramanian, Prateek Mittal

Acoustophoresis uses sound waves to manipulate small objects in mid-air and has broad potential in various applications. However, stable multi-particle levitation remains challenging due to complex acoustic dynamics and limitations of existing models. We introduce AcoustoReinforce, a reinforcement learning-based path planner that autonomously controls the motion of multiple levitated particles. Leveraging a decentralized architecture, it learns local neural policies that generate particle trajectories independently, enabling scalable, communication-free control even in densely populated acoustic fields. To ensure physical feasibility, acoustic trapping strength is incorporated as a constraint during both training and inference, producing trajectories that are collision-free, acoustically stable, and physically realizable within real-world system constraints. Experiments on a real-world levitation platform show that AcoustoReinforce outperforms state-of-the-art planners, improving task success rates by up to 130% across diverse configurations. These results demonstrate the effectiveness of learning-based decentralized control for complex multi-object acoustophoresis in real environments.

Lei Wang, Min Huang, Eduard Dragut

Aspect-Based Sentiment Intensity Analysis (ABSIA) has garnered increasing attention, though research largely focuses on domain-specific, sentence-level settings. In contrast, document-level ABSIA--particularly in addressing complex tasks like extracting Aspect-Category-Opinion-Sentiment-Intensity (ACOSI) tuples--remains underexplored. In this work, we introduce DanceHA, a multi-agent framework designed for open-ended, document-level ABSIA with informal writing styles. DanceHA has two main components: Dance, which employs a divide-and-conquer strategy to decompose the long-context ABSIA task into smaller, manageable sub-tasks for collaboration among specialized agents; and HA, Human-AI collaboration for annotation. We release Inf-ABSIA, a multi-domain document-level ABSIA dataset featuring fine-grained and high-accuracy labels from DanceHA. Extensive experiments demonstrate the effectiveness of our agentic framework and show that the multi-agent knowledge in DanceHA can be effectively transferred into student models. Our results highlight the importance of the overlooked informal styles in ABSIA, as they often intensify opinions tied to specific aspects.

Xufei Tian, Wenli Du, Shaoyi Yang, Han Hu, Hui Xin, Shifeng Qu, Ke Ye

Process simulation is a critical cornerstone of chemical engineering design. Current automated chemical design methodologies focus mainly on various representations of process flow diagrams. However, transforming these diagrams into executable simulation flowsheets remains a time-consuming and labor-intensive endeavor, requiring extensive manual parameter configuration within simulation software. In this work, we propose a novel multi-agent workflow that leverages the semantic understanding capabilities of large language models(LLMs) and enables iterative interactions with chemical process simulation software, achieving end-to-end automated simulation from textual process specifications to computationally validated software configurations for design enhancement. Our approach integrates four specialized agents responsible for task understanding, topology generation, parameter configuration, and evaluation analysis, respectively, coupled with Enhanced Monte Carlo Tree Search to accurately interpret semantics and robustly generate configurations. Evaluated on Simona, a large-scale process description dataset, our method achieves a 31. 1% improvement in the simulation convergence rate compared to state-of-the-art baselines and reduces the design time by 89. 0% compared to the expert manual design. This work demonstrates the potential of AI-assisted chemical process design, which bridges the gap between conceptual design and practical implementation. Our workflow is applicable to diverse process-oriented industries, including pharmaceuticals, petrochemicals, food processing, and manufacturing, offering a generalizable solution for automated process design.

Guokai Tang, Feng Zhao

Small language models (SLMs) run quickly, consume little memory, and can be deployed on edge devices, making them especially appealing when compute or energy is limited. Because of these advantages, boosting SLMs' reasoning ability has become an important research goal. A common approach is to distill the long chains of thought (long-CoTs) produced by large reasoning models (LRMs) into SLMs, hoping to transfer the larger models’ strong reasoning ability. However, SLMs do not always benefit from distillation of long-CoTs. The lengthy and complex semantic steps and large amount of self-reflection content in long-CoTs may exceed the limited learning capabilities of SLMs, and the impact of self-reflection density on the performance of SLMs is unclear. To resolve this capacity mismatch, we propose MACoT, a multi-agent framework that synthesizes chains of thought (CoTs) that are more suitable for small models rather than compressing or pruning existing ones. Through the interactive collaboration among six types of agents, MACoT synthesizes semantically explicit, logically clear CoTs that efficiently activate a small model’s internal knowledge through a carefully designed output pattern. At the same time, the CoTs synthesized by our method can retain a small amount of self-reflection content, thereby matching the learning capability of the small model and maximizing its reasoning accuracy. We fine-tuned Qwen2.5-7B-Instruct using only 1879 synthetic CoTs, significantly improving its performance on mathematical reasoning tasks and generalizing well, outperforming models trained on 5x more data. Through experiments, we found that a modest level of self-reflection boosts small-model performance, whereas excessive reflection sharply degrades it, which shows that “teaching SLMs to think” hinges on aligning each CoT’s cognitive load with the model’s capacity.

Yifan Su, Rishi Veerapaneni, Jiaoyang Li

Multi-Agent Path Finding (MAPF) requires computing collision-free paths for multiple agents in shared environment. Most MAPF planners assume that each agent reaches a specific location at a specific timestep, but this is infeasible to directly follow on real systems where delays often occur. To address collisions caused by agents deviating due to delays, the Temporal Plan Graph (TPG) was proposed, which converts a MAPF time dependent solution into a time independent set of inter-agent dependencies. Recently, a Bidirectional TPG (BTPG) was proposed which relaxed some dependencies into "bidirectional pairs" and improved efficiency of agents executing their MAPF solution with delays. Our work improves upon this prior work by designing an algorithm, BPTG-max, that finds more bidirectional pairs. Our main theoretical contribution is in designing the BTPG-max algorithm is locally optimal, i.e. which constructs a BTPG where no additional bidirectional pairs can be added. We also show how in practice BTPG-max leads to BTPGs with significantly more bidirectional edges, superior anytime behavior, and improves robustness to delays.

Sanchit Sinha, Guangzhi Xiong, Zhenghao He, Aidong Zhang

Modern vision-language models (VLMs) deliver impressive predictive accuracy yet offer little insight into 'why' a decision is reached, frequently hallucinating facts, particularly when encountering out-of-distribution data. Neurosymbolic frameworks address this by pairing black-box perception with interpretable symbolic reasoning, but current methods extract their symbols solely from task labels, leaving them weakly grounded in the underlying visual data. In this paper, we introduce a multi-agent system - Concept-RuleNet that reinstates visual grounding while retaining transparent reasoning. Specifically, a multimodal concept generator first mines discriminative visual concepts directly from a representative subset of training images. Next, these visual concepts are utilized to condition symbol discovery, anchoring the generations in real image statistics and mitigating label bias. Subsequently, symbols are composed into executable first-order rules by a large language model reasoner agent - yielding interpretable neurosymbolic rules. Finally, during inference, a vision verifier agent quantifies the degree of presence of each symbol and triggers rule execution in tandem with outputs of black-box neural models, predictions with explicit reasoning pathways. Experiments on five benchmarks, including two challenging medical-imaging tasks and three underrepresented natural-image datasets, show that our system augments state-of-the-art neurosymbolic baselines by an average of 5% while also reducing the occurrence of hallucinated symbols in rules by up to 50%.

Qi Shi, Pavel Naumov

A law in a multiagent system is a set of constraints imposed on agents' behaviours to avoid undesirable outcomes. The paper considers two types of laws: useful laws that, if followed, completely eliminate the undesirable outcomes and gap-free laws that guarantee that at least one agent can be held responsible each time an undesirable outcome occurs. In both cases, we study the problem of finding a law that achieves the desired result by imposing the minimum restrictions. We prove that, for both types of laws, the minimisation problem is NP-hard even in the simple case of one-shot concurrent interactions. We also show that the approximation algorithm for the vertex cover problem in hypergraphs could be used to efficiently approximate the minimum laws in both cases.

Minghao Shao, Nanda Rani, Kimberly Milner, Haoran Xi, Meet Udeshi, Saksham Aggarwal, Venkata Sai Charan Putrevu, Sandeep K. Shukla, Prashanth Krishnamurthy, Farshad Khorrami 等

Recent advances in LLM agentic systems have improved the automation of offensive security tasks, particularly for Capture the Flag (CTF) challenges. We systematically investigate the key factors that drive agent success and provide a detailed recipe for building effective LLM-based offensive security agents. First, we present CTFJudge, a framework leveraging LLM as a judge to analyze agent trajectories and provide granular evaluation across CTF solving steps. Second, we propose a novel metric, CTF Competency Index (CCI) for partial correctness, revealing how closely agent solutions align with human-crafted gold standards. Third, we examine how LLM hyperparameters, namely temperature, top-p, and maximum token length, influence agent performance and automated cybersecurity task planning. For rapid evaluation, we present CTFTiny, a curated benchmark of 50 representative CTF challenges across binary exploitation, web, reverse engineering, forensics, and cryptography. Our findings identify optimal multi-agent coordination settings and lay the groundwork for future LLM agent research in cybersecurity.

Artem Pshenitsyn, Aleksandr Panov, Alexey Skrynnik

Multi-agent reinforcement learning (MARL) is a powerful paradigm for solving cooperative and competitive decision-making problems. While many MARL benchmarks have been proposed, few combine continuous state and action spaces with challenging coordination and planning tasks. We introduce CAMAR, a new MARL benchmark designed explicitly for multi-agent pathfinding in environments with continuous actions. CAMAR supports cooperative and competitive interactions between agents and runs efficiently at up to 100,000 environment steps per second. We also propose a three-tier evaluation protocol to better track algorithmic progress and enable deeper analysis of performance. In addition, CAMAR allows the integration of classical planning methods such as RRT and RRT* into MARL pipelines. We use them as standalone baselines and combine RRT* with popular MARL algorithms to create hybrid approaches. We provide a suite of test scenarios and benchmarking tools to ensure reproducibility and fair comparison. Experiments show that CAMAR presents a challenging and realistic testbed for the MARL community.

Thomy Phan, Sven Koenig

Multi-agent path finding (MAPF) is the challenging problem of finding conflict-free paths with minimal costs for multiple agents. While traditional MAPF solvers are centralized using heuristic search, reinforcement learning (RL) is becoming increasingly popular due to its potential to learn decentralized and generalizing policies. RL-based MAPF must cope with spatial coordination, which is often addressed by combining independent training with ad hoc measures like replanning and communication. Such ad hoc measures often complicate the approach and require knowledge beyond the actual accessible information in RL, such as the full map occupation or broadcast communication channels, which limits generalizability, effectiveness, and sample efficiency. In this paper, we propose Partitioned Attention-based Reverse Curricula for Enhanced Learning (PARCEL), considering a bounding region for each agent. PARCEL trains all agents with overlapping regions jointly via self-attention to avoid potential conflicts. By employing a reverse curriculum, where the bounding regions grow as the policies improve, all agents will eventually merge into a single coordinated group. We evaluate PARCEL in two simple coordination tasks and four MAPF benchmark maps. Compared with state-of-the-art RL-based MAPF methods, PARCEL demonstrates better effectiveness and sample efficiency without ad hoc measures.