arXiv Computation and Language August 27, 2026 By Jihao Zhu, Zhiwei Yang, Wenxiao Zhang, Junqian Zhao, Qi You, Fangqi Wang, Zheyuan Deng, Hanzhe Yang, Yu Liu, Jin B. Hong

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

Read the original on arXiv Computation and Language →

ClueWeaver is a dual-agent framework designed to enable compact, locally deployable language models to answer questions about long literary narratives. The Finder agent retrieves passages that contain answer-critical clues, while the Interpreter agent derives the answer from those passages, generates rationales with paragraph-ID citations, and performs self-calibration for high-risk questions. Both agents are trained with reward-guided reinforcement learning to prioritize evidence retention, correctness, grounding, and concise explanations, resulting in improved performance and inspectability over end-to-end prompting.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Jul 22

Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning

arXiv:2607. 19345v1 Announce Type: cross Abstract: Large language models that generate step-by-step reasoning traces have achieved strong performance on complex tasks, and extending them to long-context settings has emerged as an important frontier.

By Lizhe Fang, Weizhou Shen, Tianyi Tang, Yisen Wang

llms reinforcement-learning benchmarks

Hugging Face Trending Papers

Jul 11

GRASP: GRanularity-Aware Search Policy for Agentic RAG

Agentic retrieval-augmented generation (RAG) extends static RAG by allowing language models to iteratively reason, generate search queries, retrieve evidence, and predict answers. However, it remains challenging for models to decide when to retrieve, whether to use lexical matching or semantic similarity, and how to control context granularity to prevent irrelevant tokens from interfering with agent reasoning.

llms rag agents nlp reinforcement-learning benchmarks

arXiv AI

Jul 14

GRASP: GRanularity-Aware Search Policy for Agentic RAG

arXiv:2607. 10463v1 Announce Type: new Abstract: Agentic retrieval-augmented generation (RAG) extends static RAG by allowing language models to iteratively reason, generate search queries, retrieve evidence, and predict answers.

By Varun Gandhi, Jaewook Lee, Shantanu Todmal, Franck Dernoncourt, Ryan Rossi, Zichao Wang, Andrew Lan

llms rag agents nlp reinforcement-learning benchmarks

arXiv AI

Jul 13

WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning

arXiv:2607. 09328v1 Announce Type: cross Abstract: Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across distant passages.

By Zixin Chen, Peng Liu, Haobo Li, Rui Sheng, Jianhong Tu, Xiaodong Deng, Fei Huang, Kashun Shum, Dayiheng Liu, Huamin Qu

benchmarks safety

arXiv AI

Jul 24

WildTrace: Benchmarking Natural Evidence Trails in Long-Context Reasoning

arXiv:2607. 09328v2 Announce Type: replace-cross Abstract: Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across distant passages.

By Zixin Chen, Peng Liu, Haobo Li, Rui Sheng, Jianhong Tu, Xiaodong Deng, Fei Huang, Kashun Shum, Dayiheng Liu, Huamin Qu

benchmarks safety

arXiv AI

Jun 30

HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning

arXiv:2606. 28349v1 Announce Type: cross Abstract: Long-context reasoning requires models to access, retrieve, and integrate evidence scattered across documents, dialogues, and accumulated interaction histories.

By Zeju Li, Ziyang Zheng, Yizhou Zhou, Qiang Xu

rag agents benchmarks

One email a morning, machine-written

Related stories

Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning

GRASP: GRanularity-Aware Search Policy for Agentic RAG

GRASP: GRanularity-Aware Search Policy for Agentic RAG

WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning

WildTrace: Benchmarking Natural Evidence Trails in Long-Context Reasoning

HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning