跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-12AI 評分41

LongR:透過密集效用獎勵的強化學習釋放長上下文推理能力

LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards

AI 導讀

LongR 透過動態 Think-and-Read 機制及基於相對資訊增益的上下文密度獎勵,提升大語言模型的長上下文推理能力。它在 LongBench v2 上提升超過 9%,並在 RULER 和 InfiniteBench 上持續改善。這套框架無需證據標註,並在 DAPO、GSPO 等不同強化學習演算法下均提升表現。

正文

Published on Oct 12

Authors:

,

,

,

,

,

,

,

Abstract

Reinforcement Learning (RL) has emerged as a key driver for LLM reasoning. This capability is equally pivotal in long-context scenarios---such as long-dialogue understanding and structured data analysis---where the challenge extends beyond consuming tokens to performing rigorous deduction. While existing efforts focus on data synthesis or architectural changes, recent work points out that relying solely on sparse, outcome-only rewards yields limited gains, as such coarse signals are often insufficient to effectively guide the complex long-context reasoning. To address this, we propose LongR, a unified framework that enhances long-context performance by integrating a dynamic ``Think-and-Read'' mechanism---which interleaves reasoning with document consultation---with a contextual density reward based on relative information gain to quantify the utility of the relevant documents, without evidence annotations. Empirically, LongR achieves a gain of over 9\% on LongBench v2 and consistent improvements on RULER and InfiniteBench, demonstrating robust efficiency in navigating extensive contexts. Furthermore, LongR consistently enhances performance across diverse RL algorithms (e.g., DAPO, GSPO). Finally, we conduct in-depth analyses to investigate the impact of reasoning chain length on efficiency and the model's robustness against distractors.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2602.05758

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2602.05758 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2602.05758 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2602.05758 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co