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

arXiv: https://arxiv.org/abs/2510.04373 · HTML: https://mlsanity.com/paper/2510.04373/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 31 of its 35 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 31)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?](https://mlsanity.com/paper/2403.07718/) (2024)
- [Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration](https://mlsanity.com/paper/1802.08802/) (2018)
- [Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents](https://mlsanity.com/paper/2408.07199/) (2024)
- [AdaPlanner: Adaptive Planning from Feedback with Language Models](https://mlsanity.com/paper/2305.16653/) (2023)
- [WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2505.16421/) (2025)
- [Tree Search for Language Model Agents](https://mlsanity.com/paper/2407.01476/) (2024)
- [EmbeddingGemma: Powerful and Lightweight Text Representations](https://mlsanity.com/paper/2509.20354/) (2025)
- [VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents](https://mlsanity.com/paper/2408.06327/) (2024)
- [WebPilot: A Versatile and Autonomous Multi-Agent System for Web Task Execution with Strategic Exploration](https://mlsanity.com/paper/2408.15978/) (2024)
- [WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks](https://mlsanity.com/paper/2407.05291/) (2024)
- [BM25S: Orders of magnitude faster lexical search via eager sparse scoring](https://mlsanity.com/paper/2407.03618/) (2024)
- [Beyond Browsing: API-Based Web Agents](https://mlsanity.com/paper/2410.16464/) (2024)
- [AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents](https://mlsanity.com/paper/2403.08978/) (2024)
- [AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning](https://mlsanity.com/paper/2405.16247/) (2024)
- [How to Train Your LLM Web Agent: A Statistical Diagnosis](https://mlsanity.com/paper/2507.04103/) (2025)

## Built on by (most cited first, 5 of 5)

- [Are Online Skill and Memory Modules Always Worth Their Tokens? A Budget-Constrained Study of Web Agents](https://mlsanity.com/paper/2606.15017/) (2026)
- [PREPING: Zero-Task Agent Memory Construction via Self-Practice](https://mlsanity.com/paper/2605.13880/) (2026)
- [WISE-Flow: Workflow-Induced Structured Experience for Self-Evolving Conversational Service Agents](https://mlsanity.com/paper/2601.08158/) (2026)
- [PRISM: Learning Design Knowledge from Data for Stylistic Design Improvement](https://mlsanity.com/paper/2601.11747/) (2026)
- [Grounded Skill Synthesis from Code at Scale for Agentic Intelligence](https://mlsanity.com/paper/2609.05571/) (2026)

## Abstract (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.