SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for process supervision fail to distinguish meaningful progress from mere verbosity . existing methods lack a coherent approach to process supervision . |
| Approach: | They propose a framework that formalizes reasoning as a trajectory through a state space of empirical solvability. |
| Outcome: | The proposed framework achieves an average accuracy gain of 3% with 30% reduced token consumption. |
Similar Papers
Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models (2026.findings-acl)
Copied to clipboard
Teng Wang, Jiang Zhangyi, Zhenqi He, Hailei Gong, Shenyang Tong, Wenhan Yang, Zeyu Li, Yanan Zheng, Zifan He, Zewen Ye, Shengjie Ma, Jianping Zhang
| Challenge: | Existing Process Reward Models (PRMs) are vulnerable to reward hacking and require expensive, large-scale annotation of reasoning steps. |
| Approach: | They propose a reward model approach which evaluates both individual and consecutive reasoning steps from fine-grained and coarse-grounded level. |
| Outcome: | Empirical results show that the proposed model performs better than existing PRMs and is more robust than existing models. |
Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to RLVR provide sparse supervision since reward arrives only after the full generation is complete. |
| Approach: | They propose a step-level reward system that extracts confidence and correctness and combines them into a Step Potential signal that explicitly estimates reasoning state at each step. |
| Outcome: | The proposed method outperforms existing methods on multiple benchmarks and improves accuracy while reducing response length. |
Stabilizing Efficient Reasoning with Step-Level Advantage Selection (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models generate long and verbose reasoning traces at inference time . short context post-training alone induces substantial reasoning compression . |
| Approach: | They propose a step-level advantage selection approach that reduces reasoning length by over 30% . they propose to use GRPO without any length-aware objective to train models in a shorter context window . |
| Outcome: | The proposed approach reduces average reasoning length by over 30% while improving Pass@1 accuracy by 3.79 points over the strongest length-aware baseline. |
Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work studies RLVR through token entropy, arguing that high-entropies drive exploration and should receive stronger updates. |
| Approach: | They propose a correctness-aware reinforcement framework that performs fine-grained advantage modulation over low-entropy segments. |
| Outcome: | The proposed framework improves accuracy over strong RL baselines across three backbones and six math benchmarks while maintaining high-entropy exploration. |
Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Reinforcement Learning with Verifiable Rewards (RLVR) has shown significant promise for enhancing the reasoning capabilities of large language models (LLMs). |
| Approach: | They propose a model-free method that refines credit assignment by leveraging the model's internal uncertainty signals. |
| Outcome: | Extensive experiments on five mathematical reasoning benchmarks show that the proposed method outperforms strong RLVR baselines on multiple model scales, including 1.5B and 7B. |
Learning from Cognition: Enhancing RL Efficiency for LLM Reasoning via Hierarchical Metacognitive Decomposition and Refinement (2026.acl-long)
Copied to clipboard
Zexu Sun, Yongcheng Zeng, Erxue Min, Heyang Gao, Bokai Ji, Dugang Liu, Xing Tang, Xiuqiang He, Xu Chen
| Challenge: | Recent advances in Large Language Models have demonstrated notable inferential capacities via reinforcement learning (RL) however, “zero-RL” approaches relying on fixed prompt templates introduce substantial sampling inefficiencies for weak LLMs. |
| Approach: | They propose a hierarchical metacognitive RL framework that decomposes zero-accuracy problems into subproblems and prompts the policy to refine answers by referencing previous wrong solutions. |
| Outcome: | The proposed framework improves sample utilization and sample efficiency and accelerates convergence compared to baselines. |
Exploring Layer Activation Dynamic of CoT via Knowledge Probe (2026.acl-long)
Copied to clipboard
| Challenge: | Chain-of-thought reasoning has emerged as a crucial paradigm for multi-step reasoning tasks. |
| Approach: | They propose a multi-stage probing framework that enforces structured reasoning with three explicit stages: keyword extraction, theorem generation, and computation execution. |
| Outcome: | The proposed framework enforces structured reasoning with three explicit stages: keyword extraction, theorem generation, and computation execution. |
RATIONALYST: Pre-training Process-Supervision for Improving Reasoning (2025.acl-long)
Copied to clipboard
Dongwei Jiang, Guoxuan Wang, Yining Lu, Andrew Wang, Jingyu Zhang, Chuyu Liu, Benjamin Van Durme, Daniel Khashabi
| Challenge: | RATIONALYST is a model for process-supervision of reasoning based on pretraining on rationale annotations extracted from unlabeled data. |
| Approach: | They propose a model for process-supervision of reasoning based on pre-training on rationale annotations extracted from unlabeled data. |
| Outcome: | RATIONALYST improves reasoning accuracy by 3.9% on representative reasoning benchmarks. |
ConMA : Confidence-Guided Kernel Sampling with Multi-Stage Aggregation for LLM Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to test-time scaling rely on external verifiers and one-shot independent sampling. |
| Approach: | They propose a test-time scaling framework that reallocates a fixed inference budget into iterative sample–filter–diversify–select cycles. |
| Outcome: | ConMA outperforms baselines on multiple benchmarks while converging early with only 18 samples on average, substantially reducing inference cost. |
Reason-KE++: Aligning the Process, Not Just the Outcome, for Faithful LLM Knowledge Editing (2026.findings-acl)
Copied to clipboard
| Challenge: | Current methods for modifying parameters to integrate new knowledge are not accurate enough. |
| Approach: | They propose an SFT+RL framework that instills process-level faithfulness by a stage-aware Reward mechanism and a Stage-assisted Reward Mechanism. |
| Outcome: | The proposed framework instills process-level faithfulness while boosting final accuracy. |