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

• URL: http://arxiv.org/abs/2608.25531v2
• Date: Thu, 27 Aug 2026 09:47:04 GMT
• Title: ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long Narratives
• Abstract summary: We present ClueWeaver, an evidence-aware dual-agent framework for long-narrative question answering.<n>A Finder identifies passages containing answer-critical clues through retrieval-guided segmentation.<n>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.
• Score: 10.698885109023026
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and Consolidation [50.92223196290564]
  We propose a unified agent loop for explicit evidence selection and consolidation.<n>During exploration, SCoRE retains only query-relevant observations and their source pointers in a maintained textual ledger.<n>At termination, it reloads the referenced original images and consolidates the visual evidence for answering, arranging it into a logical sequence.
  arXiv  Detail & Related papers  (2026-09-14T16:11:35Z)
• Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop Retrieval [19.37201042661162]
  We propose a training-free multi-hop retrieval framework that integrates evidence-conditioned exploration, passage-specific contrastive refinement, and coverage-aware final ranking.<n> Experiments on MuSiQue, HotpotQA, and 2WikiMultihopQA demonstrate consistent improvements in retrieval quality and downstream QA performance over baselines.
  arXiv  Detail & Related papers  (2026-09-07T05:13:56Z)
• REVEAL: A Rubric-Guided Agent for Explicit Evidence Sufficiency Verificationin Long-Video Question Answering [25.519927761448603]
  REVEAL is a rubric-guided agent framework for long-video question answering.<n>We introduce an adaptive visual-similarity-based preprocessing pipeline that groups visually coherent adjacent frames into natural event units.<n>Built upon this structured memory, REVEAL uses an automatically constructed rubric library to explicitly verify whether retrieved evidence satisfies sufficiency criteria.
  arXiv  Detail & Related papers  (2026-08-09T09:55:42Z)
• REFACT: Adaptive Fact Restatement for Compact and Faithful Chain-of-Thought Reasoning [46.43518025955049]
  Large Language Models (LLMs) increasingly leverage long-form reasoning to solve complex tasks.<n>Existing grounding approaches either append citations after generation or encourage LLMs to retrieve evidence during reasoning.<n>We propose REFACT, an adaptive fact-restatement citation framework that enables LLMs to determine when contextual grounding is needed.
  arXiv  Detail & Related papers  (2026-07-23T01:41:17Z)
• WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning [63.9071746889252]
  Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across distant passages.<n>This source-internal evidence integration is central to real-world long-document analysis, yet existing benchmarks largely sidestep it.<n>We introduce WILDTRACE, a benchmark of 481 tasks over 214 naturally occurring long-form sources.
  arXiv  Detail & Related papers  (2026-07-10T12:09:21Z)
• LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards [53.339700196282905]
  Reinforcement learning with verifiable rewards (RLVR) has shown promise for this task.<n>Existing methods are limited by low-confusability distractors and sparse, outcome-only reward signals.<n>textscLongTraceRL produces training contexts that are far more challenging than those built by random sampling or one-shot search.
  arXiv  Detail & Related papers  (2026-05-29T17:51:40Z)
• Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation [74.0621258662676]
  We propose Ptah, a multi-agent harness for interleaved report generation.<n>Ptah orchestrates the lifecycle from user query to rendered web report through planning, research, and writing stages.<n>A verifier agent serves as the harness's acceptance function, enforcing factual grounding, citation fidelity, and cross-modal consistency throughout the workflow.
  arXiv  Detail & Related papers  (2026-05-28T12:40:34Z)
• Reasoning-Augmented Representations for Multimodal Retrieval [27.4146940988752]
  Universal Multimodal Retrieval (UMR) seeks any-to-any search across text and vision.<n>We argue this brittleness is often data-specified: when images carry "silent" evidence and queries leave key semantics implicit, a single embedding pass must both reason and compress.<n>We propose a data-centric framework that decouples these roles by externalizing reasoning before retrieval.
  arXiv  Detail & Related papers  (2026-02-06T19:01:54Z)
• ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation [82.54090885503287]
  Retrieval-Augmented Generation augments Large Language Models with external knowledge to improve factuality.<n>Existing RAG systems fail to extract and integrate the key clues needed to support faithful and interpretable reasoning.<n>We propose ClueAnchor, a novel framework for enhancing RAG via clue-anchored reasoning exploration and optimization.
  arXiv  Detail & Related papers  (2025-05-30T09:18:08Z)
• GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs [6.3596531375179515]
  This paper proposes GE-Chat, a knowledge Graph enhanced retrieval-augmented generation framework to provide evidence-based response generation.<n> Specifically, when the user uploads a material document, a knowledge graph will be created, which helps construct a retrieval-augmented agent.<n>We leverage Chain-of-Thought (CoT) logic generation, n-hop sub-graph searching, and entailment-based sentence generation to realize accurate evidence retrieval.
  arXiv  Detail & Related papers  (2025-05-15T10:17:35Z)
• Unstructured Evidence Attribution for Long Context Query Focused Summarization [53.08341620504465]
  We propose to extract unstructured (i.e., spans of any length) evidence in order to acquire more relevant and consistent evidence than in the fixed granularity case.<n>We show how existing systems struggle to copy and properly cite unstructured evidence, which also tends to be "lost-in-the-middle"
  arXiv  Detail & Related papers  (2025-02-20T09:57:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.