5 papers
Capability-Driven Self-Evolution of Agent Memory
Yaoqi Chen, Yuru Feng, Qianxi Zhang +8
Memory self-evolution uses task feedback to iteratively improve executable memory programs that store and retrieve information from past interactions. Existing approaches typically…
Social Circuits behind Multi-agent Echo Chambers
Chuiyang Meng, Wenlu Yu, Ming Tang +1
Language-model agents exchange messages to combine evidence, but their communication can also create echo chambers that reinforce shared errors. However, overall task performance d…
Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents
Yaoqi Chen, Haibin Lai, Yuru Feng +12
LLM-based agents increasingly tackle long-horizon tasks with interdependent decisions, where each action reshapes future constraints and intermediate errors can cascade. Existing R…
AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories
Yifan Song, Weimin Xiong, Xiutian Zhao +6
Fine-tuning on agent-environment interaction trajectory data holds significant promise for surfacing generalized agent capabilities in open-source large language models (LLMs). In…
Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement
Weimin Xiong, Yifan Song, Xiutian Zhao +6
Large language model agents have exhibited exceptional performance across a range of complex interactive tasks. Recent approaches have utilized tuning with expert trajectories to e…