Jiawei Wang, Yucun Li, Xueqi Li, Shenghao Wang, Xinquan Gong, Dan Zhang, Zheqi Lv, Yuquan Le · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28386 · open-access PDF
Visual tool use allows vision-language models (VLMs) to acquire task-relevant evidence, but its effectiveness can be limited by predefined visual operations and the tool-use strategies learned during training. इन operations and strategies as reusable external skills allows them to be refined through self-evolution without updating model parameters. हालांकि, skill refinement can introduce performance regressions. इस बीच, accumulated task execution trajectories inspecting together with skill evolution history may lead to evolution evidence overload. इन चुनौतियों का समाधान करने के लिए
Machine translation (Meta M2M100); the English original follows.
Visual tool use enables vision-language models (VLMs) to acquire task-relevant evidence, but its effectiveness can be limited by predefined visual operations and the tool-use strategies learned during training. Representing these operations and strategies as reusable external skills allows them to be refined through self-evolution without updating model parameters. However, skill refinement can introduce performance regressions. Meanwhile, inspecting accumulated task execution trajectories together with skill evolution history may lead to evolution evidence overload. To address these challenge
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28386, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange