cd /news/artificial-intelligence/clueweaver-reward-guided-dual-agent-… · home topics artificial-intelligence article
[ARTICLE · art-112704] src=machinebrief.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

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

Researchers introduced ClueWeaver, a reward-guided dual-agent framework that improves question answering on long literary narratives using compact local language models. The framework, detailed in arXiv:2608.25531v1, uses a Finder agent to locate answer-critical passages and an Interpreter agent to derive answers with paragraph-ID citations, both optimized via reinforcement learning. Experiments show substantial gains over end-to-end local models, with code available on GitHub.

read1 min views1 publishedAug 27, 2026

arXiv:2608.25531v1 Announce Type: new 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.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @clueweaver 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/clueweaver-reward-gu…] indexed:0 read:1min 2026-08-27 ·