paper-with-me

홈 › Papers

RoiRL: Efficient, Self-Supervised Reasoning with Offline Iterative Reinforcement Learning

2025-10-03 · Aleksei Arzhantsev, Otmane Sakhi, Flavian Vasile arxiv

Reinforcement learning (RL) is central to improving reasoning in large language models (LLMs) but typically requires ground-truth rewards. Test-Time Reinforcement Learning (TTRL) removes this need by using majority-vote rewards, but relies on heavy online RL and incurs substantial computational cost. We propose RoiRL: Reasoning with offline iterative Reinforcement Learning, a family of lightweight offline learning alternatives that can target the same regularized optimal policies. Unlike TTRL, RoiRL eliminates the need to maintain a reference model and instead optimizes weighted log-likelihood objectives, enabling stable training with significantly lower memory and compute requirements. Experimental results show that RoiRL trains to 2.5x faster and consistently outperforms TTRL on reasoning benchmarks, establishing a scalable path to self-improving LLMs without labels.

📄 PDF Abstract BibTeX arXiv:2510.02892

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

On the Generalization Gap in Self-Evolving Language Model Reasoning

2026-05-31 · Zhenting Qi, Susanna Maria Baby, Stefanie Anna Baby, Kan Yuan 외 arxiv

Recent work suggests that large language models (LLMs) can improve through self-evolution (SE), using supervision signals generated by the model itself. In this work, we ask: under a strict closed-loop setup, where the s…

Logical Reasoning

Self-training Language Models for Arithmetic Reasoning

2024-07-11 · Marek Kadlčík, Michal Štefánik

Recent language models achieve impressive results in tasks involving complex multistep reasoning, but scaling these capabilities further traditionally requires expensive collection of more annotated data. In this work, w…

Arithmetic Reasoning

A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement

2026-03-20 · Yuran Li, Di Wu, Benoit Boulet arxiv

Verification-guided self-improvement has recently emerged as a promising approach to improving the accuracy of large language model (LLM) outputs. However, existing approaches face a trade-off between inference efficienc…

Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL

2022-02-09 · ICLR 2022 4 · Rui Yang, Yiming Lu, Wenzhe Li, Hao Sun 외

Solving goal-conditioned tasks with sparse rewards using self-supervised learning is promising because of its simplicity and stability over current reinforcement learning (RL) algorithms. A recent work, called Goal-Condi…

Offline RLReinforcement Learning (RL)Self-Supervised Learning

RASPRef: Retrieval-Augmented Self-Supervised Prompt Refinement for Large Reasoning Models

2026-03-27 · Rahul Soni arxiv

Recent reasoning-focused language models such as DeepSeek R1 and OpenAI o1 have demonstrated strong performance on structured reasoning benchmarks including GSM8K, MATH, and multi-hop question answering tasks. However, t…

Multi-hop Question AnsweringMathematical Reasoning