Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding

• URL: http://arxiv.org/abs/2509.06923v1
• Date: Mon, 08 Sep 2025 17:36:21 GMT
• Title: Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
• Abstract summary: Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs)<n>Existing RLVR methods often suffer from exploration inefficiency due to mismatches between the training data's difficulty and the model's capability.<n>We propose SEELE, a novel supervision-aided RLVR framework that dynamically adjusts problem difficulty to stay within the high-efficiency region.
• Score: 59.60915947702282
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, existing RLVR methods often suffer from exploration inefficiency due to mismatches between the training data's difficulty and the model's capability. LLMs fail to discover viable reasoning paths when problems are overly difficult, while learning little new capability when problems are too simple. In this work, we formalize the impact of problem difficulty by quantifying the relationship between loss descent speed and rollout accuracy. Building on this analysis, we propose SEELE, a novel supervision-aided RLVR framework that dynamically adjusts problem difficulty to stay within the high-efficiency region. SEELE augments each training sample by appending a hint (part of a full solution) after the original problem. Unlike previous hint-based approaches, SEELE deliberately and adaptively adjusts the hint length for each problem to achieve an optimal difficulty. To determine the optimal hint length, SEELE employs a multi-round rollout sampling strategy. In each round, it fits an item response theory model to the accuracy-hint pairs collected in preceding rounds to predict the required hint length for the next round. This instance-level, real-time difficulty adjustment aligns problem difficulty with the evolving model capability, thereby improving exploration efficiency. Experimental results show that SEELE outperforms Group Relative Policy Optimization (GRPO) and Supervised Fine-tuning (SFT) by +11.8 and +10.5 points, respectively, and surpasses the best previous supervision-aided approach by +3.6 points on average across six math reasoning benchmarks.

Related papers

• REVES: REvision and VErification--Augmented Training for Test-Time Scaling [53.197756110943395]
  We propose a two-stage iterative framework that alternates between online data/prompt augmentation and policy optimization.<n>We observe gains of +6.5 points over the RL baseline and +4.0 points over standard multi-turn training.
  arXiv  Detail & Related papers  (2026-06-17T10:37:23Z)
• TD-Grokking: Learning from Zero-Reward Problems by Training-Time Decomposition [10.882920019894451]
  We propose TD-Grokking, a training-time decomposition framework for zero-reward problems.<n>We show that TD-Grokking outperforms vanilla GRPO as well as all baseline approaches.
  arXiv  Detail & Related papers  (2026-06-03T06:40:04Z)
• Adaptive Multi-Expert Reasoning via Difficulty-Aware Routing and Uncertainty-Guided Aggregation [0.2864713389096699]
  This paper describes Adaptive Multi-Expert Reasoning (AMR), a framework that focuses on problem complexity by reasoning with dynamically adapted strategies.<n>An agile routing system that focuses on problem text predicts problems' difficulty and uncertainty and guides a reconfigurable sampling mechanism to manage the breadth of generation.<n>When evaluated on the GSM8K dataset, AMR achieved 75.28% accuracy while only using the original training data.
  arXiv  Detail & Related papers  (2026-04-11T19:44:57Z)
• Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems [70.94268452442147]
  Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning abilities of LLMs.<n>We propose a simple yet effective solution based on task reformulation.<n>We introduce Cog-DRIFT, a framework that constructs reformulated variants and organizes them into an adaptive curriculum.
  arXiv  Detail & Related papers  (2026-04-06T15:38:38Z)
• Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability [129.1296673737603]
  Large language models (LLMs) have demonstrated strong reasoning capabilities through step-by-step chain-of-thought (CoT) reasoning.<n>A potential alternative is divide-and-conquer (DAC) reasoning, which decomposes a complex problem into subproblems to facilitate more effective exploration of the solution.<n>We propose an end-to-end reinforcement learning (RL) framework to enhance their DAC-style reasoning capacity.
  arXiv  Detail & Related papers  (2026-02-02T18:54:54Z)
• Think Right: Learning to Mitigate Under-Over Thinking via Adaptive, Attentive Compression [68.69801176669843]
  We propose an online post-training RL method that prunes redundant steps and estimates difficulty.<n> TRAAC (Think Right with Adaptive, Attentive Compression) achieves an average absolute accuracy gain of 8.4%.<n>Although our models are trained on math datasets, they show accuracy and efficiency gains on out-of-distribution non-math datasets.
  arXiv  Detail & Related papers  (2025-10-02T02:00:20Z)
• Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning [37.20632079882874]
  We introduce Difficulty Aware Certainty guided Exploration (DACE)<n>It balances the exploration exploitation trade-off based on the policys success rate.<n>Experiments on challenging mathematical reasoning benchmarks (AIME, MATH) show that DACE significantly outperforms strong baselines.
  arXiv  Detail & Related papers  (2025-08-29T08:57:54Z)
• RL for Reasoning by Adaptively Revealing Rationales [36.50924054394857]
  Supervised fine-tuning (SFT) relies on dense ground-truth labels, which become increasingly costly as sequence length grows.<n>We address this by adaptive backtracking (AdaBack), a per-sample curriculum learning algorithm that reveals only a partial prefix of the target output during training.<n>We show that our adaptive curriculum over partial answers reliably solves problems that are otherwise intractable.
  arXiv  Detail & Related papers  (2025-06-22T17:46:14Z)
• Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay [61.823835392216544]
  Reinforcement learning (RL) has become an effective approach for fine-tuning large language models (LLMs)<n>We propose two techniques to improve data efficiency in LLM RL fine-tuning: difficulty-targeted online data selection and rollout replay.<n>Our method reduces RL fine-tuning time by 25% to 65% to reach the same level of performance as the original GRPO algorithm.
  arXiv  Detail & Related papers  (2025-06-05T17:55:43Z)
• TACO: Think-Answer Consistency for Optimized Long-Chain Reasoning and Efficient Data Learning via Reinforcement Learning in LVLMs [50.820065021136024]
  DeepSeek R1 has significantly advanced complex reasoning for large language models (LLMs)<n>Recent methods have attempted to replicate R1's reasoning capabilities in multimodal settings.<n>We propose TACO, a novel reinforcement learning algorithm for visual reasoning.
  arXiv  Detail & Related papers  (2025-05-27T06:30:48Z)
• PATS: Process-Level Adaptive Thinking Mode Switching [53.53401063490537]
  Current large-language models (LLMs) typically adopt a fixed reasoning strategy, either simple or complex, for all questions, regardless of their difficulty.<n>This neglect of variation in task and reasoning process complexity leads to an imbalance between performance and efficiency.<n>Existing methods attempt to implement training-free fast-slow thinking system switching to handle problems of varying difficulty, but are limited by coarse-grained solution-level strategy adjustments.<n>We propose a novel reasoning paradigm: Process-Level Adaptive Thinking Mode Switching (PATS), which enables LLMs to dynamically adjust their reasoning strategy based on the difficulty of each step, optimizing the balance between
  arXiv  Detail & Related papers  (2025-05-25T17:58:50Z)
• Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective [27.94738910330893]
  Reinforcement learning exhibits potential in enhancing the reasoning abilities of large language models.<n>Existing methods attempt to improve efficiency by scheduling problems based on problem difficulties.<n>This paper introduces $textbfC$ompetence-$textbfD$ifficulty, which enables accurate and stable estimation of problem difficulties.
  arXiv  Detail & Related papers  (2025-05-23T09:15:26Z)
• Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT? [59.418994222096885]
  We conduct a detailed analysis of model performance on the AIME24 dataset.<n>We categorize questions into four tiers (Easy, Medium, Hard, and Extremely Hard)<n>We find that progression from Easy to Medium tier requires adopting an R1 reasoning style with minimal SFT-1K instances.<n>Exh-level questions present a fundamentally different challenge; they require unconventional problem-solving skills.
  arXiv  Detail & Related papers  (2025-04-16T03:39:38Z)
• Generalization Guarantees for Neural Architecture Search with Train-Validation Split [48.265305046655996]
  This paper explores the statistical aspects of such problems with train-validation splits. We show that refined properties of the validation loss such as risk and hyper-gradients are indicative of those of the true test loss. We also highlight rigorous connections between NAS, multiple kernel learning, and low-rank matrix learning.
  arXiv  Detail & Related papers  (2021-04-29T06:11:00Z)

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.