{"total":32,"rows":[{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627,"area":null},{"id":"2505.07775","title":"Must Read: A Comprehensive Survey of Computational Persuasion","created":"2025-05-12","cited_by_count":13,"area":null},{"id":"2605.07073","title":"TeamBench: Evaluating Agent Coordination under Enforced Role Separation","created":"2026-05-08","cited_by_count":10,"area":null},{"id":"2604.27043","title":"CL-bench Life: Can Language Models Learn from Real-Life Context?","created":"2026-04-29","cited_by_count":9,"area":null},{"id":"2605.28655","title":"AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation","created":"2026-05-27","cited_by_count":9,"area":null},{"id":"2604.11523","title":"PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints","created":"2026-04-13","cited_by_count":7,"area":null},{"id":"2510.17149","title":"ProtocolBench: Which LLM MultiAgent Protocol to Choose?","created":"2025-10-20","cited_by_count":6,"area":null},{"id":"2601.10567","title":"Generative AI collective behavior needs an interactionist paradigm","created":"2026-01-15","cited_by_count":6,"area":null},{"id":"2505.15068","title":"ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2601.13206","title":"Real-Time Deadlines Reveal Fragile Temporal Adaptation in LLM Strategic Dialogues","created":"2026-01-19","cited_by_count":5,"area":null},{"id":"2601.22184","title":"Tacit Coordination of Large Language Models","created":"2026-01-28","cited_by_count":5,"area":null},{"id":"2608.06867","title":"LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers","created":"2026-08-07","cited_by_count":4,"area":null},{"id":"2604.05523","title":"Market-Bench: Benchmarking Large Language Models on Economic and Trade Competition","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2604.23459","title":"Architecture Matters for Multi-Agent Security","created":"2026-04-25","cited_by_count":3,"area":null},{"id":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2507.10142","title":"Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2606.00804","title":"Dynamic Coordination Strategy Selection for Enterprise Multi-Agent Systems","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2606.09800","title":"FASE: Fast Adaptive Semantic Entropy for Code Quality","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2608.09819","title":"Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2609.31877","title":"A Large-Scale Benchmark and Risk Assessment of Traffic Analysis Attacks on Cloud LLM Services","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2609.32192","title":"CoMemBench: Benchmarking Collaborative Memory Boundaries across Multi-Agent Workflow Topologies","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2602.00307","title":"Autonomous Data Processing using Meta-Agents","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.13275","title":"Artificial Organisations","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2605.13172","title":"When Does Hierarchy Help? Benchmarking Agent Coordination in Event-Driven Industrial Scheduling","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2606.27233","title":"Bridging Talk and Thought: Understanding Dialogue Dynamics Across Collaborative Problem-Solving Contexts","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.25656","title":"OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simulation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.14870","title":"JarvisBench: Always-on Intelligence Between Humans and Agents","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.02191","title":"Examining the Vulnerability of Multi-Agent Medical Systems to Human Interventions for Clinical Reasoning","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2610.00583","title":"Worse Together: How Performance Breaks Down in Multi-User Multi-Agent Teams","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01244","title":"Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaboration","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04053","title":"The Cost of a Hop: Benchmarking NLIP and A2A","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.14021","title":"CoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}