paper-with-me

홈 › Papers

ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long Narratives

2026-08-26 · Jihao Zhu, Zhiwei Yang, Wenxiao Zhang, Junqian Zhao, Qi You, Fangqi Wang, Zheyuan Deng, Hanzhe Yang, Yu Liu, Jin B. Hong arxiv

Humanities and social science research requires close reading of long narrative materials such as novels, scripts, archives, and case reports, yet many users have limited access to costly proprietary long-context models. Compact, locally deployable language models are a practical alternative, but directly feeding them an entire long context remains costly, hard to inspect, and prone to missing sparse evidence. We present ClueWeaver, an evidence-aware dual-agent framework for long-narrative question answering with compact local models. A Finder identifies passages containing answer-critical clues through retrieval-guided segmentation, while an Interpreter derives the answer from the selected evidence, produces rationales with paragraph-ID citations, and applies an internal self-calibration pass for high-risk questions. Both agents are optimized with reward-guided reinforcement learning: Finder rewards emphasize evidence retention and faithful paragraph-ID references, and Interpreter rewards emphasize correctness, grounding, and concise explanations. This decomposition makes evidence selection and reasoning more inspectable than end-to-end prompting. Experiments across multiple long-context narrative question answering and claim verification settings show that ClueWeaver substantially improves local end-to-end language models while providing evidence coverage and paragraph-referenced reasoning traces. Code is available at https://github.com/Ameame1/ClueWeaver.

📄 PDF Abstract BibTeX arXiv:2608.25531

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningQuestion Answering

Similar Papers 제목 키워드 기반

Faithful Mobile GUI Agents with Guided Advantage Estimator

2026-05-02 · Haowen Hu, Pengzhou Cheng, Zheng Wu, Lingzhong Dong 외 arxiv

Vision-language model based graphical user interface (GUI) agents have shown strong interaction capabilities. However, they often behave unfaithfully, relying on memorized shortcuts rather than grounding actions in displ…

Can David Beat Goliath? On Multi-Hop Reasoning with Resource-Constrained Agents

2026-01-29 · Hojae Han, Heeyun Jung, Jongyoon Kim, Seung-won Hwang arxiv

Multi-turn reasoning agents solve complex questions by decomposing them into intermediate retrieval or tool-use steps, for accumulating supporting evidence across turns. Meanwhile, with reinforcement learning (RL), train…

Reinforcement Learning

LLM-Based Offline Learning for Embodied Agents via Consistency-Guided Reward Ensemble

2024-11-26 · Yujeong Lee, Sangwoo Shin, Wei-Jin Park, Honguk Woo

Employing large language models (LLMs) to enable embodied agents has become popular, yet it presents several limitations in practice. In this work, rather than using LLMs directly as agents, we explore their use as tools…

Offline RLReinforcement Learning (RL)

SmartSnap: Proactive Evidence Seeking for Self-Verifying Agents

2025-12-26 · Shaofei Cai, Yulei Qin, Haojia Lin, Zihan Xu 외 arxiv

Agentic reinforcement learning (RL) holds great promise for the development of autonomous agents under complex GUI tasks, but its scalability remains severely hampered by the verification of task completion. Existing tas…

Reinforcement Learning

Learning to Bid Long-Term: Multi-Agent Reinforcement Learning with Long-Term and Sparse Reward in Repeated Auction Games

2022-04-05 · Jing Tan, Ramin Khalili, Holger Karl

We propose a multi-agent distributed reinforcement learning algorithm that balances between potentially conflicting short-term reward and sparse, delayed long-term reward, and learns with partial information in a dynamic…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning (RL)