{"total":92,"rows":[{"id":"2505.23885","title":"OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation","created":"2025-05-29","cited_by_count":131,"area":"lr"},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2505.08638","title":"TRAIL: Trace Reasoning and Agentic Issue Localization","created":"2025-05-13","cited_by_count":104,"area":"lr"},{"id":"2412.01928","title":"MALT: Improving Reasoning with Multi-Agent LLM Training","created":"2024-12-02","cited_by_count":76,"area":"lr"},{"id":"2311.11797","title":"Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents","created":"2023-11-20","cited_by_count":72,"area":"lr"},{"id":"2311.08152","title":"Towards Reasoning in Large Language Models via Multi-Agent Peer Review Collaboration","created":"2023-11-14","cited_by_count":51,"area":"lr"},{"id":"2503.03686","title":"MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems","created":"2025-03-05","cited_by_count":50,"area":"lr"},{"id":"2401.10568","title":"CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents","created":"2024-01-19","cited_by_count":42,"area":"lr"},{"id":"2410.18963","title":"OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning","created":"2024-10-24","cited_by_count":38,"area":"lr"},{"id":"2411.04329","title":"CodeTree: Agent-guided Tree Search for Code Generation with Large Language Models","created":"2024-11-07","cited_by_count":34,"area":"lr"},{"id":"2503.02390","title":"ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks","created":"2025-03-04","cited_by_count":31,"area":"lr"},{"id":"2504.09772","title":"Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning","created":"2025-04-14","cited_by_count":29,"area":"lr"},{"id":"2312.04854","title":"Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System","created":"2023-12-08","cited_by_count":26,"area":"lr"},{"id":"2503.23064","title":"VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language Models","created":"2025-03-29","cited_by_count":26,"area":"lr"},{"id":"2409.03155","title":"Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models","created":"2024-09-05","cited_by_count":19,"area":"lr"},{"id":"2505.11556","title":"Systematic Failures in Collective Reasoning under Distributed Information in Multi-Agent LLMs","created":"2025-05-15","cited_by_count":19,"area":"lr"},{"id":"2507.17842","title":"Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning","created":"2025-07-23","cited_by_count":19,"area":"lr"},{"id":"2511.13288","title":"Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO","created":"2025-11-17","cited_by_count":18,"area":"lr"},{"id":"2508.00890","title":"AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks","created":"2025-07-26","cited_by_count":16,"area":"lr"},{"id":"2510.15414","title":"MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs","created":"2025-10-17","cited_by_count":16,"area":"lr"},{"id":"2602.08847","title":"Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems","created":"2026-02-09","cited_by_count":16,"area":"lr"},{"id":"2506.09790","title":"ComfyUI-R1: Exploring Reasoning Models for Workflow Generation","created":"2025-06-11","cited_by_count":15,"area":"lr"},{"id":"2402.18439","title":"Beyond Natural Language: LLMs Leveraging Alternative Formats for Enhanced Reasoning and Communication","created":"2024-02-28","cited_by_count":14,"area":"lr"},{"id":"2405.18208","title":"A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models","created":"2024-05-28","cited_by_count":12,"area":"lr"},{"id":"2606.00765","title":"FALAT: Tracing Failures in LLM Agent Trajectories via Dependency-Guided Search","created":"2026-05-30","cited_by_count":12,"area":"lr"},{"id":"2412.15305","title":"Tree-of-Code: A Tree-Structured Exploring Framework for End-to-End Code Generation and Execution in Complex Task Handling","created":"2024-12-19","cited_by_count":11,"area":"lr"},{"id":"2511.06345","title":"PRAGMA: A Profiling-Reasoned Multi-Agent Framework for Automatic Kernel Optimization","created":"2025-11-09","cited_by_count":11,"area":"lr"},{"id":"2606.10662","title":"Decentralized Multi-Agent Systems with Shared Context","created":"2026-06-09","cited_by_count":10,"area":"lr"},{"id":"2410.21359","title":"Can Machines Think Like Humans? A Behavioral Evaluation of LLM Agents in Dictator Games","created":"2024-10-28","cited_by_count":9,"area":"lr"},{"id":"2509.21199","title":"A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA","created":"2025-09-25","cited_by_count":9,"area":"lr"},{"id":"2506.15695","title":"SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models","created":"2025-05-28","cited_by_count":8,"area":"lr"},{"id":"2603.07379","title":"SoK: Agentic Retrieval-Augmented Generation (RAG): Taxonomy, Architectures, Evaluation, and Research Directions","created":"2026-03-07","cited_by_count":8,"area":"lr"},{"id":"2410.01504","title":"PersonaMath: Boosting Mathematical Reasoning via Persona-Driven Data Augmentation","created":"2024-10-02","cited_by_count":7,"area":"lr"},{"id":"2504.20464","title":"A Survey on GUI Agents with Foundation Models Enhanced by Reinforcement Learning","created":"2025-04-29","cited_by_count":7,"area":"lr"},{"id":"2507.01702","title":"AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness","created":"2025-07-02","cited_by_count":7,"area":"lr"},{"id":"2512.23167","title":"SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2505.17673","title":"Rethinking Agent Design: From Top-Down Workflows to Bottom-Up Skill Evolution","created":"2025-05-23","cited_by_count":6,"area":"lr"},{"id":"2510.12838","title":"A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning","created":"2025-10-13","cited_by_count":6,"area":"lr"},{"id":"2406.14629","title":"Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study","created":"2024-06-20","cited_by_count":5,"area":"lr"},{"id":"2510.17922","title":"Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Models","created":"2025-10-20","cited_by_count":5,"area":"lr"},{"id":"2510.19245","title":"See, Think, Act: Online Shopper Behavior Simulation with VLM Agents","created":"2025-10-22","cited_by_count":5,"area":"lr"},{"id":"2512.07132","title":"DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning","created":"2025-12-08","cited_by_count":5,"area":"lr"},{"id":"2602.01797","title":"ORCH: many analyses, one merge-a deterministic multi-agent orchestrator for discrete-choice reasoning with EMA-guided routing","created":"2026-02-02","cited_by_count":5,"area":"lr"},{"id":"2607.25996","title":"RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models","created":"2026-07-28","cited_by_count":5,"area":"lr"},{"id":"2405.17129","title":"TEII: Think, Explain, Interact and Iterate with Large Language Models to Solve Cross-lingual Emotion Detection","created":"2024-05-27","cited_by_count":4,"area":"lr"},{"id":"2506.05813","title":"MAPLE: Multi-Agent Adaptive Planning with Long-Term Memory for Table Reasoning","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2508.02121","title":"A Survey on AgentOps: Categorization, Challenges, and Future Directions","created":"2025-08-04","cited_by_count":4,"area":"lr"},{"id":"2604.21304","title":"PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs","created":"2026-04-23","cited_by_count":4,"area":"lr"},{"id":"2504.06460","title":"Can LLMs Simulate Personas with Reversed Performance? A Systematic Investigation for Counterfactual Instruction Following in Math Reasoning Context","created":"2025-04-08","cited_by_count":3,"area":"lr"},{"id":"2505.18831","title":"Enhancing LLMs' Reasoning-Intensive Multimedia Search Capabilities through Fine-Tuning and Reinforcement Learning","created":"2025-05-24","cited_by_count":3,"area":"lr"},{"id":"2601.07780","title":"Enhancing Self-Correction in Large Language Models through Multi-Perspective Reflection","created":"2026-01-12","cited_by_count":3,"area":"lr"},{"id":"2601.09667","title":"Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning","created":"2026-01-14","cited_by_count":3,"area":"lr"},{"id":"2601.15047","title":"Game-Theoretic Lens on LLM-based Multi-Agent Systems","created":"2026-01-21","cited_by_count":3,"area":"lr"},{"id":"2603.15661","title":"DynaTrust: Defending Multi-Agent Systems Against Sleeper Agents via Dynamic Trust Graphs","created":"2026-03-09","cited_by_count":3,"area":"lr"},{"id":"2605.22566","title":"GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving","created":"2026-05-21","cited_by_count":3,"area":"lr"},{"id":"2606.29194","title":"AI Trading's Alpha Singularity: Emergent Market Reasoning through Agent-to-Agent Self-Evolution","created":"2026-06-28","cited_by_count":3,"area":"lr"},{"id":"2406.04464","title":"On The Importance of Reasoning for Context Retrieval in Repository-Level Code Editing","created":"2024-06-06","cited_by_count":2,"area":"lr"},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2602.03026","title":"Visual Reasoning over Time Series via Multi-Agent System","created":"2026-02-03","cited_by_count":2,"area":"lr"},{"id":"2604.11045","title":"Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable Infrastructure","created":"2026-04-13","cited_by_count":2,"area":"lr"},{"id":"2605.01133","title":"When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems","created":"2026-05-01","cited_by_count":2,"area":"lr"},{"id":"2609.05933","title":"Rethinking the Evaluation of Efficiency Methods for Multi-Agent Systems","created":"2026-09-05","cited_by_count":2,"area":"lr"},{"id":"2403.18230","title":"Large Language Models Need Consultants for Reasoning: Becoming an Expert in a Complex Human System Through Behavior Simulation","created":"2024-03-27","cited_by_count":1,"area":"lr"},{"id":"2508.02841","title":"A Multi-Agent System for Complex Reasoning in Radiology Visual Question Answering","created":"2025-08-04","cited_by_count":1,"area":"lr"},{"id":"2602.13370","title":"G2CP: A Graph-Grounded Communication Protocol for Verifiable and Efficient Multi-Agent Reasoning","created":"2026-02-13","cited_by_count":1,"area":"lr"},{"id":"2604.17419","title":"ARMove: Learning to Predict Human Mobility through Agentic Reasoning","created":"2026-04-19","cited_by_count":1,"area":"lr"},{"id":"2604.20658","title":"Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2605.19418","title":"Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2606.29026","title":"Preventing Error Propagation in Multi-Agent AI through Runtime Monitoring","created":"2026-06-27","cited_by_count":1,"area":"lr"},{"id":"2607.28225","title":"FaithEyes: Towards Faithful Tool Use via Multi-Agent Process-Image Verification","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2510.01674","title":"FOR-Prompting: From Objection to Revision via an Asymmetric Prompting Protocol","created":"2025-10-02","cited_by_count":0,"area":"lr"},{"id":"2510.05746","title":"ARM: Discovering Agentic Reasoning Modules for Generalizable Multi-Agent Systems","created":"2025-10-07","cited_by_count":0,"area":"lr"},{"id":"2511.22598","title":"LLM-Cave: A benchmark and light environment for large language models reasoning and decision-making system","created":"2025-11-27","cited_by_count":0,"area":"lr"},{"id":"2512.08300","title":"rSIM: Incentivizing Reasoning Capabilities of LLMs via Reinforced Strategy Injection","created":"2025-12-09","cited_by_count":0,"area":"lr"},{"id":"2601.04556","title":"4D-ARE: Bridging the Attribution Gap in LLM Agent Requirements Engineering","created":"2026-01-08","cited_by_count":0,"area":"lr"},{"id":"2601.14053","title":"LLMOrbit: A Circular Taxonomy of Large Language Models -From Scaling Walls to Agentic AI Systems","created":"2026-01-20","cited_by_count":0,"area":"lr"},{"id":"2602.02979","title":"CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning","created":"2026-02-03","cited_by_count":0,"area":"lr"},{"id":"2602.09173","title":"$n$-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models","created":"2026-02-09","cited_by_count":0,"area":"lr"},{"id":"2602.23610","title":"LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoning","created":"2026-02-27","cited_by_count":0,"area":"lr"},{"id":"2603.18470","title":"CyberJustice Tutor: An Agentic AI Framework for Cybersecurity Learning via Think-Plan-Act Reasoning and Pedagogical Scaffolding","created":"2026-03-19","cited_by_count":0,"area":"lr"},{"id":"2603.20270","title":"FactorSmith: Agentic Simulation Generation via Markov Decision Process Decomposition with Planner-Designer-Critic Refinement","created":"2026-03-15","cited_by_count":0,"area":"lr"},{"id":"2605.11404","title":"Attributing Emergence in Million-Agent Systems","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.15016","title":"COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2606.04823","title":"R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search","created":"2026-06-03","cited_by_count":0,"area":"lr"},{"id":"2606.05158","title":"Streaming Communication in Multi-Agent Reasoning","created":"2026-06-03","cited_by_count":0,"area":"lr"},{"id":"2606.15931","title":"DeepRoot: A KG-Coordinated Multi-Agent System for Therapeutic Reasoning over Historical Medical Texts","created":"2026-06-14","cited_by_count":0,"area":"lr"},{"id":"2606.16328","title":"AdaSTORM: Scaling LLM Reasoning on Dynamic Graphs via Adaptive Spatio-Temporal Multi-Agent Collaboration","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2607.11696","title":"Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction","created":"2026-07-13","cited_by_count":0,"area":"lr"},{"id":"2607.23678","title":"Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph Systems","created":"2026-07-26","cited_by_count":0,"area":"lr"},{"id":"2609.19759","title":"Rethinking Multi-Agent Collaboration: When More Is Less","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2609.32700","title":"CAIRN: Dynamic Fact-Intent DAGs for Multi-Agent Exploration","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2610.17869","title":"ECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}