ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning

• URL: http://arxiv.org/abs/2608.28771v1
• Date: Fri, 28 Aug 2026 18:28:50 GMT
• Title: ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning
• Abstract summary: We propose a two-phase RLVR framework for large reasoning models.<n>The first phase trains with the Entropy Relief Reward (ERR), a bonus proportional to cumulative token-level entropy drops in the thinking phase.<n>The second phase introduces the Robust Relative Efficiency Reward, which scores each response's length against co-generated peers.
• Score: 13.033342249823022
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large reasoning models achieve strong performance on complex tasks by generating extended chain-of-thought (CoT) traces via reinforcement learning with verifiable rewards (RLVR). While current RLVR methods have achieved strong results with correctness-based reward signals, they provide limited guidance on the quality of the reasoning process itself, leaving the internal reasoning structure largely unoptimized. Through empirical analysis across multiple model families, we identify a consistent pattern: correct reasoning trac es exhibit more frequent and larger token-level entropy drops within the thinking phase than incorrect ones. We propose ERR+, a two-phase RLVR framework grounded in this observation. The first phase trains with the Entropy Relief Reward (ERR), a bonus proportional to cumulative token-level entropy drops in the thinking phase, log-normalized by response length. Unlike prior methods that suppress entropy, ERR rewards the resolution of uncertainty while leaving exploratory high-entropy states unconstrained. The second phase introduces the Robust Relative Efficiency Reward, which scores each response's length against co-generated peers via a $\tanh$-transformed within-group $z$-score. We provide a formal analysis showing that joint optimization of the two objectives induces gradient conflict in early training, motivating the sequential design . Experiments on five datasets demonstrate consistent improvements in both accuracy and response conciseness across model backbones. Our code is available at https://github.com/XrkArul/err_response

Related papers

• Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning [63.36243250685778]
  Conditional Entropy Shaping (CES) is a framework that dynamically controls token-level response entropy.<n>CES consistently improves average accuracy while reducing response length relative to DAPO.
  arXiv  Detail & Related papers  (2026-05-19T04:41:51Z)
• Recursive Think-Answer Process for LLMs and VLMs [54.52289112197118]
  We propose an efficient Recursive Think-Answer Process (R-TAP)<n>R-TAP enables models to engage in iterative reasoning cycles and generate more accurate answers.<n>We show that R-TAP-enhanced models consistently outperform conventional single-pass methods.
  arXiv  Detail & Related papers  (2026-03-02T17:20:10Z)
• APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards [61.52322047892064]
  Test-Time Scaling (TTS) has significantly enhanced the capabilities of Large Reasoning Models (LRMs)<n>We observe that LRMs frequently conduct repetitive self-verification without revision even after obtaining the final answer during the reasoning process.<n>We propose Anchor-based Process Reward (APR), a structure-aware reward shaping method that localizes the reasoning anchor and penalizes exclusively the post-anchor AST.
  arXiv  Detail & Related papers  (2026-01-31T14:53:20Z)
• ProRAG: Process-Supervised Reinforcement Learning for Retrieval-Augmented Generation [54.071574153853994]
  ProRAG is a process-supervised reinforcement learning framework designed to integrate learned step-level supervision into the online optimization loop.<n>Our framework consists of four stages: (1) Supervised Policy Warmup to initialize the model with a structured reasoning format; (2) construction of an MCTS-based Process Reward Model (PRM) to quantify intermediate reasoning quality; (3) PRM-Guided Reasoning Refinement to align the policy with fine-grained process preferences; and (4) Process-Supervised Reinforcement Learning with a dual-granularity advantage mechanism.
  arXiv  Detail & Related papers  (2026-01-29T16:04:59Z)
• Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs [6.948242693954442]
  Reinforcement Learning with Verifiable Rewards (RLVR) has become a central approach for improving the reasoning ability of large language models.<n>We propose LESS, a correctness-aware reinforcement framework that performs fine-grained advantage modulation over low-entropy segments.
  arXiv  Detail & Related papers  (2025-11-30T14:19:36Z)
• DeCoRL: Decoupling Reasoning Chains via Parallel Sub-Step Generation and Cascaded Reinforcement for Interpretable and Scalable RLHF [11.39724102247425]
  We present DeCoRL (Decoupled Reasoning Chains via Coordinated Reinforcement Learning), a novel framework that transforms reasoning from sequential processing into collaborative modular orchestration.<n>DeCoRL trains lightweight specialized models to generate reasoning sub-steps concurrently, eliminating sequential bottlenecks through parallel processing.<n> Comprehensive evaluation demonstrates state-of-the-art results across RM-Bench, RMB, and RewardBench, outperforming existing methods including large-scale models.
  arXiv  Detail & Related papers  (2025-11-11T07:52:39Z)
• PEAR: Phase Entropy Aware Reward for Efficient Reasoning [23.381346604897246]
  This paper introduces Phase Entropy Aware Reward (PEAR), a reward mechanism that incorporates phase-dependent entropy into the reward design.<n>Experiments across four benchmarks demonstrate that PEAR consistently reduces response length while sustaining competitive accuracy across model scales.
  arXiv  Detail & Related papers  (2025-10-09T10:04:31Z)
• CURE: Critical-Token-Guided Re-Concatenation for Entropy-Collapse Prevention [24.71056659948577]
  We introduce CURE (Critical-token-gUided Re concatenation for Entropy-collapse prevention), a two-stage framework that balances exploration and exploitation.<n>CURE achieves a 5% performance gain across six math benchmarks, establishing state-of-the-art performance in both entropy and accuracy.
  arXiv  Detail & Related papers  (2025-08-14T18:40:34Z)
• Intra-Trajectory Consistency for Reward Modeling [67.84522106537274]
  We develop an intra-trajectory consistency regularization to enforce that adjacent processes with higher next-token generation probability maintain more consistent rewards.<n>We show that the reward model trained with the proposed regularization induces better DPO-aligned policies and achieves better best-of-N (BON) inference-time verification results.
  arXiv  Detail & Related papers  (2025-06-10T12:59:14Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.