{"ID":2860418,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04373","arxiv_id":"2510.04373","title":"JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptation","abstract":"Large language model (LLM) agents perform well in sequential decision-making tasks, but improving them on unfamiliar domains often requires costly online interactions or fine-tuning on large expert datasets. These strategies are impractical for closed-source models and expensive for open-source ones, with risks of catastrophic forgetting. Offline trajectories offer reusable knowledge, yet demonstration-based methods struggle because raw traces are long, noisy, and tied to specific tasks. We present Just-in-time Episodic Feedback Hinter (JEF-Hinter), an agentic system that distills offline traces into compact, context-aware hints. A zooming mechanism highlights decisive steps in long trajectories, capturing both strategies and pitfalls. Unlike prior methods, JEF-Hinter leverages both successful and failed trajectories, extracting guidance even when only failure data is available, while supporting parallelized hint generation and benchmark-independent prompting. At inference, a retriever selects relevant hints for the current state, providing targeted guidance with transparency and traceability. Experiments on MiniWoB++, WorkArena-L1, and WebArena-Lite show that JEF-Hinter consistently outperforms strong baselines, including human- and document-based hints.","short_abstract":"Large language model (LLM) agents perform well in sequential decision-making tasks, but improving them on unfamiliar domains often requires costly online interactions or fine-tuning on large expert datasets. These strategies are impractical for closed-source models and expensive for open-source ones, with risks of cata...","url_abs":"https://arxiv.org/abs/2510.04373","url_pdf":"https://arxiv.org/pdf/2510.04373v2","authors":"[\"Hadi Nekoei\",\"Aman Jaiswal\",\"Patrice Bechard\",\"Oleh Shliazhko\",\"Orlando Marquez Ayala\",\"Mathieu Reymond\",\"Massimo Caccia\",\"Alexandre Drouin\",\"Sarath Chandar\",\"Alexandre Lacoste\"]","published":"2025-10-05T21:34:42Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}