Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

• URL: http://arxiv.org/abs/2512.16912v2
• Date: Sun, 21 Dec 2025 17:23:35 GMT
• Title: Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
• Authors: Peter Chen, Xiaopeng Li, Ziniu Li, Wotao Yin, Xi Chen, Tianyi Lin,
• Abstract summary: The paper examines the exploration-exploitation trade-off in reinforcement learning with verifiable rewards (RLVR)<n>Recent studies suggest that RLVR can elicit strong mathematical reasoning in Large Language Models (LLMs)<n>Our findings clarify the mechanisms behind spurious-reward benefits and provide principles for more effective RLVR training.
• Score: 33.74512650901766
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper examines the exploration-exploitation trade-off in reinforcement learning with verifiable rewards (RLVR), a framework for improving the reasoning of Large Language Models (LLMs). Recent studies suggest that RLVR can elicit strong mathematical reasoning in LLMs through two seemingly paradoxical mechanisms: spurious rewards, which suppress exploitation by rewarding outcomes unrelated to the ground truth, and entropy minimization, which suppresses exploration by pushing the model toward more confident and deterministic outputs, highlighting a puzzling dynamic: both discouraging exploitation and discouraging exploration improve reasoning performance, yet the underlying principles that reconcile these effects remain poorly understood. We focus on two fundamental questions: (i) how policy entropy relates to performance, and (ii) whether spurious rewards yield gains, potentially through the interplay of clipping bias and model contamination. Our results show that clipping bias under spurious rewards reduces policy entropy, leading to more confident and deterministic outputs, while entropy minimization alone is insufficient for improvement. We further propose a reward-misalignment model explaining why spurious rewards can enhance performance beyond contaminated settings. Our findings clarify the mechanisms behind spurious-reward benefits and provide principles for more effective RLVR training.

Related papers

• ICPO: Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning [17.98065634130798]
  We propose the Intrinsic Confidence-Driven Group Relative Preference Optimization method (ICPO)<n>ICPO calculates a preference advantage score for each response by comparing the relative generation probabilities of multiple responses under the same input prompt.<n>We have discovered that the preference advantage score not only alleviates the issues of coarse-grained rewards and reward noise but also effectively curbs overconfident errors.
  arXiv  Detail & Related papers  (2025-11-26T03:10:15Z)
• Revisiting Entropy in Reinforcement Learning for Large Reasoning Models [54.96908589622163]
  We investigate the entropy dynamics of large language models trained withReinforcement learning with verifiable rewards (RLVR)<n>Our findings reveal that the number of off-policy updates, the diversity of training data, and the clipping thresholds in the optimization objective are critical factors influencing the entropy of LLMs trained with RLVR.
  arXiv  Detail & Related papers  (2025-11-08T12:50:41Z)
• PACR: Progressively Ascending Confidence Reward for LLM Reasoning [55.06373646059141]
  We propose Progressively Ascending Confidence Reward (PACR)<n>PACR is a dense, model-intrinsic reward computed directly from the model's evolving belief in the correct answer.<n>Our results suggest that dense, model-intrinsic shaping signals can make RLVR training more effective and reliable.
  arXiv  Detail & Related papers  (2025-10-25T11:25:35Z)
• VAR: Visual Attention Reasoning via Structured Search and Backtracking [49.427842994857635]
  We introduce Visual Attention Reasoning, a framework that recasts grounded reasoning as a structured search.<n> VAR decomposes the reasoning process into two key stages: traceable evidence grounding and search-based chain-of-thought.<n>We show that our 7B model, VAR-7B, sets a new state-of-the-art on a comprehensive suite of hallucination and safety benchmarks.
  arXiv  Detail & Related papers  (2025-10-21T13:18:44Z)
• Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking [78.69179041551014]
  We propose an information-theoretic reward modeling framework based on the Information Bottleneck principle.<n>We show that InfoRM filters out preference-irrelevant information to alleviate reward misgeneralization.<n>We also introduce IBL, a distribution-level regularization that penalizes such deviations, effectively expanding the optimization landscape.
  arXiv  Detail & Related papers  (2025-10-15T15:51:59Z)
• Rediscovering Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning [55.59724323303857]
  We propose a framework that balances exploration and exploitation via three components: difficulty-aware coefficient allocation, initial-anchored target entropy, and dynamic global coefficient adjustment.<n>Experiments on multiple mathematical reasoning benchmarks show that AER consistently outperforms baselines, improving both reasoning accuracy and exploration capability.
  arXiv  Detail & Related papers  (2025-10-13T03:10:26Z)
• Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning [20.0162100611394]
  We introduce UnCertainty-aware Advantage Shaping (UCAS), a model-free method that refines credit assignment by leveraging the model's internal uncertainty signals.<n>UCAS operates in two stages: it first modulates the response-level advantage using the model's overall self-confidence, and then applies a token-level penalty based on raw logit certainty.<n>Our analysis confirms that UCAS not only achieves higher rewards but also promotes greater reasoning diversity and successfully mitigates entropy collapse.
  arXiv  Detail & Related papers  (2025-10-12T15:06:53Z)
• CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models [85.315711639214]
  We introduce Curiosity-Driven Exploration (CDE), a framework that leverages the model's own intrinsic sense of curiosity to guide exploration.<n>For the actor, we use perplexity over its generated response, and for the critic, we use the variance of value estimates from a multi-head architecture.<n>Our theoretical analysis shows that the actor-wise bonus inherently penalizes overconfident errors and promotes diversity among correct responses.
  arXiv  Detail & Related papers  (2025-09-11T17:59:17Z)
• Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs [35.27561531876348]
  This paper systematically investigates the impact of Reinforcement Learning with Verifiable Rewards (RLVR) on Large Language Models (LLMs)<n>We show that RLVR can extend the reasoning boundary for both mathematical and coding tasks.<n>We present a theoretical framework explaining RLVR's incentive mechanism, demonstrating how it can encourage correct reasoning even when rewards are based solely on answer correctness.
  arXiv  Detail & Related papers  (2025-06-17T07:06:56Z)
• Navigate the Unknown: Enhancing LLM Reasoning with Intrinsic Motivation Guided Exploration [39.460202867967006]
  We propose an Intrinsic Motivation guidEd exploratioN meThOd foR LLM Reasoning (i-MENTOR) to deliver dense rewards and amplify exploration in the RL-based paradigm.<n>Experiments across 4 public datasets demonstrate i-MENTOR's effectiveness, achieving a 22.23% improvement on AIME 2024.
  arXiv  Detail & Related papers  (2025-05-23T08:30:28Z)

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.