Agent skills encapsulate reusable procedural knowledge that enables LLM agents to perform tasks, and they can be improved automatically using trajectories from interactions with the environment. This is the classic problem of skill evolution. Existing approaches predominately follow a linear evolution paradigm, in whic...
Kai-Wei Liu, Ji-Qian Dong, Li-Ran Dong et al.· 0 citations
Agents tend to optimize, select, or constrain execution structures before decisive runtime outcomes are observed. However, such pre-execution commitment creates an orchestration bottleneck: when intermediate evidence invalidates the pending continuation, agents must either execute stale steps or replan broadly, compoun...
Tian-Xing Wang, Ming-Ming Zhao, Shuai Huang et al.· 1 citation
Results on diverse long-horizon benchmarks demonstrate the efficacy of ScienceFlow's ability to sustain effective research processes, and demonstrates that efficient state management, adaptive exploration, and objective-aligned execution are critical for scaling autonomous research beyond short-horizon interactions.
Ming-Ming Zhao, Jiqian Dong, Kangping Xu et al.· 0 citations
Hierarchical Graph Retrieval-Augmented Generation (GraphRAG) organizes corpus knowledge at multiple levels of granularity, yet fixed context construction may fail to translate these multi-resolution representations into a context suited to the current query. We identify this mismatch as the representation--inference ga...
Yong-Feng Huang, Yuren Lai, Rui-Ying Chen et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.