LaSeR: Reinforcement Learning with Last-Token Self-Rewarding

• URL: http://arxiv.org/abs/2510.14943v1
• Date: Thu, 16 Oct 2025 17:55:11 GMT
• Title: LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
• Authors: Wenkai Yang, Weijie Liu, Ruobing Xie, Yiju Guo, Lulu Wu, Saiyong Yang, Yankai Lin,
• Abstract summary: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs)<n>Previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which significantly reduces efficiency.<n>We propose LaSeR (Reinforcement Learning with Last-Token Self-Rewarding), an algorithm that simply augments the original RLVR loss with a MSE loss.
• Score: 54.72617309922891
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a core paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). To address the lack of verification signals at test time, prior studies incorporate the training of model's self-verification capability into the standard RLVR process, thereby unifying reasoning and verification capabilities within a single LLM. However, previous practice requires the LLM to sequentially generate solutions and self-verifications using two separate prompt templates, which significantly reduces efficiency. In this work, we theoretically reveal that the closed-form solution to the RL objective of self-verification can be reduced to a remarkably simple form: the true reasoning reward of a solution is equal to its last-token self-rewarding score, which is computed as the difference between the policy model's next-token log-probability assigned to any pre-specified token at the solution's last token and a pre-calculated constant, scaled by the KL coefficient. Based on this insight, we propose LaSeR (Reinforcement Learning with Last-Token Self-Rewarding), an algorithm that simply augments the original RLVR loss with a MSE loss that aligns the last-token self-rewarding scores with verifier-based reasoning rewards, jointly optimizing the reasoning and self-rewarding capabilities of LLMs. The optimized self-rewarding scores can be utilized in both training and testing to enhance model performance. Notably, our algorithm derives these scores from the predicted next-token probability distribution of the last token immediately after generation, incurring only the minimal extra cost of one additional token inference. Experiments show that our method not only improves the model's reasoning performance but also equips it with remarkable self-rewarding capability, thereby boosting its inference-time scaling performance.

Related papers

• SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification [28.63435151584449]
  We propose SelfJudge, which trains judge verifiers via self-supervision of the target model.<n>Our method measures semantic preservation by assessing whether token-substituted responses preserve the meaning of original responses.
  arXiv  Detail & Related papers  (2025-09-26T02:21:12Z)
• ConfClip: Confidence-Weighted and Clipped Reward for Reinforcement Learning in LLMs [32.13266235550995]
  Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs)<n>Inspired by observations from human learning, we introduce a RL technique that integrates verifiable outcomes with the model's own confidence estimates.
  arXiv  Detail & Related papers  (2025-09-22T13:00:35Z)
• Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner [24.152878302325508]
  We introduce the reward-shifted speculative sampling (SSS) algorithm, in which the draft model is aligned with human preferences, while the target model remains unchanged.<n>Our algorithm achieves superior gold reward scores at a significantly reduced inference cost in test-time weak-to-strong alignment experiments.
  arXiv  Detail & Related papers  (2025-08-20T20:10:56Z)
• CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment [44.33395106709674]
  Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of Large Language Models (LLMs) by using rule-based binary feedback.<n>Current RLVR methods typically assign the same reward to every token.<n>This coarse-grained feedback hampers precise credit assignment, making it hard for models to identify which reasoning steps lead to success or failure.
  arXiv  Detail & Related papers  (2025-08-04T11:06:08Z)
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
  We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
  arXiv  Detail & Related papers  (2025-03-04T18:56:03Z)
• Scalable Best-of-N Selection for Large Language Models via Self-Certainty [65.31658824274894]
  Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models.<n>We propose self-certainty, a novel and efficient metric to estimate response quality without requiring external reward models.<n>Our findings establish self-certainty as a practical and efficient way for improving LLM reasoning capabilities.
  arXiv  Detail & Related papers  (2025-02-25T19:08:07Z)
• S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning [51.84977135926156]
  We introduce S$2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference.<n>Our results demonstrate that Qwen2.5-math-7B achieves an accuracy improvement from 51.0% to 81.6%, outperforming models trained on an equivalent amount of long-CoT distilled data.
  arXiv  Detail & Related papers  (2025-02-18T13:40:22Z)
• Self-Improvement in Language Models: The Sharpening Mechanism [70.9248553790022]
  We offer a new perspective on the capabilities of self-improvement through a lens we refer to as sharpening.<n>Motivated by the observation that language models are often better at verifying response quality than they are at generating correct responses, we formalize self-improvement as using the model itself as a verifier during post-training.<n>We analyze two natural families of self-improvement algorithms based on SFT and RLHF.
  arXiv  Detail & Related papers  (2024-12-02T20:24:17Z)
• An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking [50.81324768683995]
  FIRST is a novel approach that integrates a learning-to-rank objective and leveraging the logits of only the first generated token. We extend the evaluation of FIRST to the TREC Deep Learning datasets (DL19-22), validating its robustness across diverse domains. Our experiments confirm that fast reranking with single-token logits does not compromise out-of-domain reranking quality.
  arXiv  Detail & Related papers  (2024-11-08T12:08:17Z)

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.