SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs

• URL: http://arxiv.org/abs/2605.18864v1
• Date: Fri, 15 May 2026 07:42:21 GMT
• Title: SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs
• Abstract summary: reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yield comparable gains in pass@k.<n>We argue that a central structural constraint arises from reverse-KL regularization, which stabilizes training but inherently anchors the policy to the reference distribution.<n>We propose SAGE, a principled framework that enables controllable empirical support expansion by reshaping the reverse-KL anchor distribution itself.
• Score: 55.46289074417954
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent studies observe that reinforcement learning with verifiable rewards (RLVR) reliably improves pass@1 on reasoning tasks, yet often fails to yield comparable gains in pass@k, raising the question of whether RLVR genuinely enables large language models to acquire novel reasoning abilities or merely enhances the efficiency of sampling reasoning modes already present in the base model. Prior analyses largely support the latter view, attributing this limitation to structural properties of standard RLVR objectives that result in insufficient exploration pressure. In this work, we argue that a central structural constraint arises from reverse-KL regularization, which stabilizes training but inherently anchors the policy to the reference distribution, thereby suppressing the emergence of alternative reasoning modes. However, we show that neither removing the KL term nor replacing it with forward-KL provides a satisfactory solution, as both disrupt the efficiency-coverage trade-off by either inducing reward hacking or allocating probability mass to off-target regions. To resolve this tension, we propose SAGE, a principled framework that enables controllable empirical support expansion by reshaping the reverse-KL anchor distribution itself through a guide function q(x,y), achieving consistent improvements in both pass@1 and pass@k across challenging mathematical reasoning benchmarks. Our code is available at https://github.com/tally0818/SAGE.

Related papers

• Boosting LLM Exploration via Weak-Model Guidance in RLVR [36.33733929880283]
  We propose a simple yet effective approach to preserve the generative diversity of LLMs during RLVR.<n>Instead of relying solely on internal exploration, we force the target model to generate answers based on partial reasoning trajectories generated by a smaller, weaker language models.<n>Our approach efficiently mitigates entropy collapse without requiring additional SFT, intricate reward designs, or complex prompting.
  arXiv  Detail & Related papers  (2026-08-27T17:45:50Z)
• Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning [58.088509347353465]
  Reinforcement learning (RL) fine-tuning is widely used in language model training.<n>We propose a game-theoretic framework that gives this trade-off an explicit statistical interpretation.
  arXiv  Detail & Related papers  (2026-07-29T00:19:09Z)
• ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples [65.74946647574696]
  Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs)<n>In this work, we investigate a critical source of this instability: over-optimization.<n>We propose ARMOR, a framework that shifts the paradigm from passive penalty to active sample stabilization.
  arXiv  Detail & Related papers  (2026-07-11T21:22:46Z)
• Understanding Diversity Collapse in RLVR via the Lens of Overtraining [78.37408098404312]
  Reinforcement learning with verifiable rewards (RLVR) has become a key approach for enhancing the reasoning abilities of large language models.<n>We formalize this diversity collapse through the lens of emphovertraining<n>We propose emphBayesian Boundary Gating (BBG) which redirects optimization away from overtraining by estimating each problem's marginal contribution to the reasoning boundary.
  arXiv  Detail & Related papers  (2026-06-13T20:13:37Z)
• Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data [55.84428098924793]
  We propose Constrained Uniform Top-K Sampling (CUTS), a parameter-free decoding strategy enforcing structure-preserving exploration.<n>We integrate this into Mixed-CUTS, a training framework synergizing exploitative and exploratory rollouts to amplify intra-group advantage variance.<n> Notably, Mixed-CUTS improves Pass@1 accuracy on the challenging AIME25 benchmark by up to 15.1% over standard GRPO.
  arXiv  Detail & Related papers  (2026-04-20T16:43:28Z)
• Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning [88.42566960813438]
  CalibRL is a hybrid-policy RLVR framework that supports controllable exploration with expert guidance.<n>CalibRL increases policy entropy in a guided manner and clarifies the target distribution.<n>Experiments across eight benchmarks, including both in-domain and out-of-domain settings, demonstrate consistent improvements.
  arXiv  Detail & Related papers  (2026-02-22T07:23:36Z)
• Beyond Reasoning Gains: Mitigating General Capabilities Forgetting in Large Reasoning Models [33.214586668992965]
  Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning.<n>We propose RECAP-a replay strategy with dynamic objective reweighting for general knowledge.<n>Our method is end-to-end and readily applicable to existing RLVR pipelines without training additional models or heavy tuning.
  arXiv  Detail & Related papers  (2025-10-24T19:08:48Z)
• Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration [8.839121572048018]
  We propose RAPO, an algorithm to promote broader yet focused exploration.<n>We train Qwen2.5-3B and 7B models with RAPO on the 8K SimpleRL-Zero dataset.<n>Results show that RAPO consistently improves problem-solving performance.
  arXiv  Detail & Related papers  (2025-10-04T16:22:19Z)
• The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward [57.56453588632619]
  A central paradox in fine-tuning Large Language Models (LLMs) with Reinforcement Learning with Verifiable Reward (RLVR) is the frequent degradation of multi-attempt performance.<n>This is often accompanied by catastrophic forgetting, where models lose previously acquired skills.<n>We argue that standard RLVR objectives lack a crucial mechanism for knowledge retention.
  arXiv  Detail & Related papers  (2025-09-09T06:34:32Z)
• The Invisible Leash: Why RLVR May or May Not Escape Its Origin [47.488691410579925]
  It remains unclear whether the current practice of RLVR truly expands a model's reasoning boundary.<n>Under current training conditions, RLVR can operate as a support-constrained optimization mechanism.<n>While RLVR reliably enhances precision, it may progressively narrow exploration and potentially overlook correct yet underrepresented solutions.
  arXiv  Detail & Related papers  (2025-07-20T07:04:08Z)

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.