Papers with Multi-Agent Systems
AgentMaster: A Multi-Agent Conversational Framework Using A2A and MCP Protocols for Multimodal Information Retrieval and Analysis (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Recent advances in AI focus on multi-agent systems (MAS) that can be integrated with Large Language Models (LLMs) but current systems still face challenges of inter-agency communication, coordination, and interaction with heterogeneous tools and resources. |
| Approach: | They propose a modular multi-protocol MAS framework with self-implemented A2A and MCP . the framework supports natural language interaction without prior technical expertise . |
| Outcome: | The proposed framework supports natural language interaction without prior technical expertise and responds to multimodal queries for tasks including information retrieval, question answering, and image analysis. |
Thesis Proposal: A Multi-Agent System for Ontology-Based Perspective-Aware Knowledge Extraction (2026.eacl-srw)
Copied to clipboard
| Challenge: | Current AI systems consolidate multiple perspectives into singular, decontextualized schemas, introducing representational bias and information loss. |
| Approach: | They propose a framework to operationalize perspective-aware knowledge extraction using ontologies and Large Language Models. |
| Outcome: | The proposed framework can operationalize perspective-aware knowledge extraction without representational bias and information loss. |
Grammar Search for Multi-Agent Systems (2026.acl-long)
Copied to clipboard
Mayank Singh, Vikas Yadav, Shiva Krishna Reddy Malay, Shravan Nayak, Sai Rajeswar, Sathwik Tejaswi Madhusudhan, Eduardo Blanco
| Challenge: | Several prior approaches have relied on LLM-based free-form search over the code space. |
| Approach: | They propose a more structured framework that explores the same space through a fixed set of composable components. |
| Outcome: | The proposed framework outperforms existing approaches on most benchmarks across two backbone LLMs and two domains: mathematics and question answering. |
Towards Self-Improving Error Diagnosis in Multi-Agent Systems (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing diagnostic approaches rely on expensive expert annotations and ”LLM-as-a-judge” paradigms. |
| Approach: | They propose a framework for semantic failure attribution that identifies responsible agents and the originating error step. |
| Outcome: | The proposed framework outperforms baselines in step-level localization and validation. |
PEAR: Planner-Executor Agent Robustness Benchmark (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies examine isolated attack surfaces or specific scenarios, leaving a lack of holistic understanding of MAS vulnerabilities. |
| Approach: | They propose a benchmark to evaluate the utility and vulnerability of planner–executor MAS. |
| Outcome: | The proposed benchmark evaluates planner–executor MAS on a widely adopted design. |
Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches generate workflows either at task level or query level, but their relative costs and benefits remain unclear. |
| Approach: | They propose a query-level workflow generation framework that generates tasks at task level and query level. |
| Outcome: | The proposed framework reduces token usage by up to 83% compared to existing approaches . it maintains competitive performance with an average degradation of just 0.61% compared with existing approaches across multiple datasets . |
Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization (2026.findings-acl)
Copied to clipboard
Yueyang Cang, Xiaoteng Zhang, Erlu Zhao, Zehua Ji, Yuhang Liu, Yuchen He, Zhiyuan Ning, Chen Yijun, Wenge Que, Li Shi
| Challenge: | Recent approaches to optimize communication topology rely on single-sample policy gradients with absolute rewards. |
| Approach: | They propose a topology optimization framework that integrates Group Relative Policy Optimization. |
| Outcome: | The proposed topology optimization framework outperforms state-of-the-art methods on reasoning and code generation benchmarks. |
LinguaGame: A Linguistically Grounded Game-Theoretic Paradigm for Multi-Agent Dialogue Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have enabled Multi-Agent Systems (MASs) where agents interact through natural language to solve complex tasks or simulate multi-party dialogues. |
| Approach: | They propose a linguistically-grounded game-theoretic paradigm for multi-agent dialogue generation that uses a training-free equilibrium approximation algorithm to model dialogue over communicative intents and strategies. |
| Outcome: | The proposed framework improves agents’ communication efficiency by helping them convey their intended meaning more effectively through language. |
The Adaptive Interrogator: Detecting Trojan LLMs in Multi-Agent Systems via Evolved Conversational Strategies (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been focused on single-agent, white-box environments, but multi-agend systems (MAS) have a critical blind spot: supply chain vulnerabilities. |
| Approach: | They propose a black-box auditing framework that leverages an Evolutionary Algorithm to autonomously expose hidden threats. |
| Outcome: | The proposed framework achieves superior detection rates (up to 100% in specific configurations) and robustness across diverse architectures. |
TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM Systems (2026.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks and datasets focus on single-agent settings, failing to capture the unique vulnerabilities of multi-agend LLM dynamics and co-ordination. |
| Approach: | They propose a benchmark to evaluate the robustness and safety of multi-agent LLM systems. |
| Outcome: | The proposed benchmark evaluates the robustness and safety of multi-agent LLM systems. |
RouterHGC: Optimized Router for LLM-based Multi-Agent Systems via Heterogeneous Graph Contrastive Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs)-driven Multi-Agent Systems (MAS) have demonstrated remarkable scalability and generalizability across complex tasks. |
| Approach: | They propose a new framework for routing using large language models . they formalize routing as node selection through edge-weight prediction . |
| Outcome: | The proposed framework outperforms the best single LLM and baselines on five datasets . it achieves 0.80%–6.17% accuracy gains on MATH and HotpotQA while reducing inference cost by 27.40%. |
Single-Agent Generation Surpasses Multi-Agent Systems in Semantic Diversity (2026.findings-acl)
Copied to clipboard
| Challenge: | Multi-Agent Systems (MAS) are used to improve reasoning diversity and robustness by simulating interactions among agents with distinct roles. |
| Approach: | They find that a Multi-Output strategy produces the highest diversity without degrading logical validity. |
| Outcome: | The proposed approach outperforms multi-agent systems in semantic diversity . the results point to a more efficient and effective way to expand diversity - the authors say . |
Nash-Pruned CredMAS: Dynamic Panel Pruning for VLM-MAS using Nash-based Selection and Doubly-Robust Credits (2026.findings-acl)
Copied to clipboard
| Challenge: | Multi-Agent Systems (MAS) are expensive due to static panel designs, where all N agents communicate at every T round. |
| Approach: | They propose an economic framework that transforms agent selection into a dynamic resource allocation game. |
| Outcome: | The proposed system reduces token consumption by over 25% on challenging benchmarks while reducing token consumption. |