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

arXiv: https://arxiv.org/abs/2602.05758 · HTML: https://mlsanity.com/paper/2602.05758/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 22 of 22)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention](https://mlsanity.com/paper/2506.13585/) (2025)
- [Reward Design with Language Models](https://mlsanity.com/paper/2303.00001/) (2023)
- [MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent](https://mlsanity.com/paper/2507.02259/) (2025)
- [DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models](https://mlsanity.com/paper/2309.14509/) (2023)
- [Kimi Linear: An Expressive, Efficient Attention Architecture](https://mlsanity.com/paper/2510.26692/) (2025)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)
- [GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning](https://mlsanity.com/paper/2504.00891/) (2025)
- [MiniCPM4: Ultra-Efficient LLMs on End Devices](https://mlsanity.com/paper/2506.07900/) (2025)
- [Reward Reasoning Model](https://mlsanity.com/paper/2505.14674/) (2025)
- [Generalist Reward Models: Found Inside Large Language Models](https://mlsanity.com/paper/2506.23235/) (2025)
- [SeerAttention-R: Sparse Attention Adaptation for Long Reasoning](https://mlsanity.com/paper/2506.08889/) (2025)
- [LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts](https://mlsanity.com/paper/2510.19363/) (2025)
- [RewardAnything: Generalizable Principle-Following Reward Models](https://mlsanity.com/paper/2506.03637/) (2025)
- [QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management](https://mlsanity.com/paper/2512.12967/) (2025)
- [Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning](https://mlsanity.com/paper/2601.10306/) (2026)

## Built on by (most cited first, 10 of 10)

- [Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks](https://mlsanity.com/paper/2604.02795/) (2026)
- [LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning](https://mlsanity.com/paper/2604.14922/) (2026)
- [LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards](https://mlsanity.com/paper/2605.31584/) (2026)
- [InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain](https://mlsanity.com/paper/2606.03329/) (2026)
- [Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents](https://mlsanity.com/paper/2606.05263/) (2026)
- [Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning](https://mlsanity.com/paper/2606.18831/) (2026)
- [Evidence-State Rewards for Long-Context Reasoning](https://mlsanity.com/paper/2607.02073/) (2026)
- [Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning](https://mlsanity.com/paper/2607.19345/) (2026)
- [JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models](https://mlsanity.com/paper/2607.17572/) (2026)
- [LongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management](https://mlsanity.com/paper/2610.13075/) (2026)

## Abstract (arXiv)

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.