# Revisiting LLM Reasoning via Information Bottleneck

arXiv: https://arxiv.org/abs/2507.18391 · HTML: https://mlsanity.com/paper/2507.18391/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models](https://mlsanity.com/paper/2505.22617/) (2025)
- [Reasoning with Exploration: An Entropy Perspective](https://mlsanity.com/paper/2506.14758/) (2025)
- [The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning](https://mlsanity.com/paper/2505.15134/) (2025)
- [Skywork Open Reasoner 1 Technical Report](https://mlsanity.com/paper/2505.22312/) (2025)
- [Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models](https://mlsanity.com/paper/2506.06395/) (2025)
- [Reinforcement Learning Finetunes Small Subnetworks in Large Language Models](https://mlsanity.com/paper/2505.11711/) (2025)
- [Diversity-Aware Policy Optimization for Large Language Model Reasoning](https://mlsanity.com/paper/2505.23433/) (2025)
- [One-shot Entropy Minimization](https://mlsanity.com/paper/2505.20282/) (2025)
- [Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them](https://mlsanity.com/paper/2507.10616/) (2025)
- [Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training](https://mlsanity.com/paper/2507.12507/) (2025)
- [Memorization-Compression Cycles Improve Generalization](https://mlsanity.com/paper/2505.08727/) (2025)

## Built on by (most cited first, 19 of 19)

- [Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning](https://mlsanity.com/paper/2508.16949/) (2025)
- [No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping](https://mlsanity.com/paper/2509.21880/) (2025)
- [Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory](https://mlsanity.com/paper/2602.18297/) (2026)
- [Self-Aligned Reward: Towards Effective and Efficient Reasoners](https://mlsanity.com/paper/2509.05489/) (2025)
- [A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization](https://mlsanity.com/paper/2601.22718/) (2026)
- [PEAR: Phase Entropy Aware Reward for Efficient Reasoning](https://mlsanity.com/paper/2510.08026/) (2025)
- [ReLaX: Reasoning with Latent Exploration for Large Reasoning Models](https://mlsanity.com/paper/2512.07558/) (2025)
- [The Effectiveness of Approximate Regularized Replay for Efficient Supervised Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2512.22337/) (2025)
- [Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck](https://mlsanity.com/paper/2603.10351/) (2026)
- [Topic Identification in LLM Input-Output Pairs through the Lens of Information Bottleneck](https://mlsanity.com/paper/2509.03533/) (2025)
- [Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization](https://mlsanity.com/paper/2510.16022/) (2025)
- [Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck](https://mlsanity.com/paper/2603.08462/) (2026)
- [Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization](https://mlsanity.com/paper/2607.14614/) (2026)
- [From generative AI to the brain: five takeaways](https://mlsanity.com/paper/2511.16432/) (2025)
- [Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority](https://mlsanity.com/paper/2602.01227/) (2026)
- [When Less is Enough: Efficient Inference via Collaborative Reasoning](https://mlsanity.com/paper/2605.01111/) (2026)
- [Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization](https://mlsanity.com/paper/2605.28109/) (2026)
- [Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction](https://mlsanity.com/paper/2607.11696/) (2026)
- [Limits of Reliability and Scaling in Language Models](https://mlsanity.com/paper/2607.14112/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have recently demonstrated remarkable progress in reasoning capabilities through reinforcement learning with verifiable rewards (RLVR). By leveraging simple rule-based rewards, RL effectively incentivizes LLMs to produce extended chain-of-thought (CoT) reasoning trajectories, progressively guiding them toward correct answers. However, existing approaches remain largely heuristic and intuition-driven, limiting the development of principled methodologies. In this paper, we present a theoretical characterization of LLM reasoning grounded in information bottleneck (IB) principle, introducing IB-aware reasoning optimization (IBRO), a framework that encourages reasoning trajectories to be both informative about the final correct answer and generalizable across diverse prompts. We derive a practical token-level surrogate objective and propose an efficient approximation, resulting in the lightweight IB regularization method. This technique integrates seamlessly into existing RL-based post-training frameworks without additional computational overhead, requiring only a one-line code modification. Empirically, we validate IB regularization across multiple mathematical reasoning benchmarks and RL algorithms, demonstrating consistent improvements in LLM reasoning performance.