paper-with-me

홈 › Papers

JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptation

2025-10-05 · Hadi Nekoei, Aman Jaiswal, Patrice Bechard, Oleh Shliazhko, Orlando Marquez Ayala, Mathieu Reymond, Massimo Caccia, Alexandre Drouin, Sarath Chandar, Alexandre Lacoste arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.04373

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models

2018-02-16 · ICML 2018 7 · Marine Le Morvan, Jean-Philippe Vert

Learning sparse linear models with two-way interactions is desirable in many application domains such as genomics. l1-regularised linear models are popular to estimate sparse models, yet standard implementations fail to …

Sim2O: Efficient Offline-to-Online MARL via Joint Action Composition

2026-06-19 · Bingchang Song, Yiqin Yang arxiv

Offline-to-online adaptation serves as a pivotal paradigm for mitigating the prohibitive cost of online exploration by bootstrapping reinforcement learning from offline datasets. While this paradigm has been extensively …

Multi-agent Reinforcement Learning

OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis

2026-07-27 · Zihan Li, Feiyang Liu, Dandan Shan, Ruibo Wang 외 hf

Biomedical image analysis spans diverse modalities and tasks, yet real-world deployment is hindered by severe distribution shifts across scanners, protocols, and patient populations. High-performing models consequently r…

Test-time Adaptation

Offline Meta Reinforcement Learning with In-Distribution Online Adaptation

2023-05-31 · Jianhao Wang, Jin Zhang, Haozhe Jiang, Junyu Zhang 외

Recent offline meta-reinforcement learning (meta-RL) methods typically utilize task-dependent behavior policies (e.g., training RL agents on each individual task) to collect a multi-task dataset. However, these methods a…

Meta Reinforcement Learningreinforcement-learningReinforcement LearningUncertainty Quantification

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

2025-10-06 · Qizheng Zhang, Changran Hu, Shubhangi Upasani, Boyuan Ma 외 arxiv

Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior…