4 papers
Do LLM Agents Negotiate Rationally? A Mechanism-Design Framework for Verifiable Multi-Agent Interaction over A2A/MCP
Wael Albayaydh, Rui Zhao
Modern LLM-agent frameworks increasingly interoperate through standards such as Anthropic's Model Context Protocol (MCP) for agent-to-tool access and Google's Agent2Agent (A2A) pro…
Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents
Wael Albayaydh, Rui Zhao, Ivan Flechais
Large language model (LLM) agents are increasingly evaluated on their ability to use tools, plan multi-step tasks, coordinate with other agents, and operate over extended horizons.…
Performance-guided Reinforced Active Learning for Object Detection
Zhixuan Liang, Xingyu Zeng, Rui Zhao +1
Active learning (AL) strategies aim to train high-performance models with minimal labeling efforts, only selecting the most informative instances for annotation. Current approaches…
Aligning Data Selection with Performance: Performance-driven Reinforcement Learning for Active Learning in Object Detection
Zhixuan Liang, Xingyu Zeng, Rui Zhao +1
Active learning strategies aim to train high-performance models with minimal labeled data by selecting the most informative instances for labeling. However, existing methods for as…