Online Self-Weighted Fine‑Tuning (OSW‑FT) augments standard supervised fine‑tuning by adding online, trajectory‑level weighting: for each query the model estimates its current success rate from a small number of inference‑only rollouts and rescales the SFT loss accordingly. The method keeps the optimization direction anchored to the expert trajectory while adapting the update magnitude online, and it is shown to be unbiased for any finite rollout count with a convergence analysis. Across Qwen3 models from 0.6B to 4B, OSW‑FT consistently outperforms plain SFT on challenging benchmarks such as AIME, achieving a favorable compute‑performance trade‑off with only two online rollouts.
arXiv:2604. 01170v2 Announce Type: replace-cross Abstract: While test-time scaling has enabled large language models to solve highly difficult tasks, state-of-the-art results come at exorbitant compute costs.
arXiv:2607. 28457v1 Announce Type: cross Abstract: Scaling test-time computation can improve language-model reasoning, but uniform budgets waste computation on easy inputs, while verifier-guided refinement relies on external feedback.
ReST‑RL introduces a unified Reinforced Self‑Training (ReST) policy‑value framework that enhances large language model (LLM) reasoning by combining an optimized ReST‑style GRPO algorithm with a value‑guided search (VM‑MCTS). The ReST‑GRPO component reshapes trajectory distributions to increase reward variance and expose policies to more informative partial states, improving training efficiency. VM‑MCTS trains a Value Model from self‑collected Monte‑Carlo Tree Search targets and uses it during inference to provide precise process signals and verification scores, boosting reasoning accuracy across coding benchmarks and out‑of‑domain math and science tasks.
arXiv:2604. 02621v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) substantially improves the reasoning capabilities of language models, but most existing RL fine-tuning approaches rely entirely on ground-truth verifiable rewards and thus labeled datasets with verifiable answers.
arXiv:2606. 01281v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs).
arXiv:2601. 22448v2 Announce Type: replace Abstract: RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts are sampled and when.
The paper introduces Single‑Rollout Pass@k Policy Optimization (SR‑PPO), a reinforcement learning method that uses only one rollout per prompt to train language‑model agents. SR‑PPO combines Monte Carlo token‑level advantage estimation with Pass@k gradient reweighting and an online critic for baseline and weight estimation. Experiments show that SR‑PPO achieves stable learning and performance comparable to traditional Group Relative Policy Optimization (GRPO) on reasoning and logic benchmarks, even when off‑policy drift degrades standard Pass@1 PPO.
arXiv:2603.00578v2 Announce Type: replace-cross Abstract: Long chain-of-thought~(CoT) reasoning improves the problem-solving capability of large reasoning models~(LRMs), but often incurs substantial...
arXiv:2608. 16072v1 Announce Type: cross Abstract: Reinforcement learning (RL) with group-relative advantages has become the de facto standard for post-training language model reasoners.
arXiv:2609.37119v1 Announce Type: cross Abstract: Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instabilit...
The paper introduces Verifiable Process Rewards (VPR), a framework that uses symbolic or algorithmic task-solving oracles as action-level verifiers to provide dense rewards for intermediate actions in agentic reasoning tasks. VPR is applied to Sokoban, Sudoku, and Minesweeper, and improves policy performance over outcome-reward baselines. The authors also demonstrate VPR’s effectiveness in a tool‑use benchmark, highlighting its reliance on reliable task oracles and the difficulty of extending it to less structured environments.
The paper introduces Cross-Behavior Policy Optimization (CBPO), a method that unifies offline demonstrations and policy-generated rollouts into a single regression loss using a fixed-reference target. CBPO eliminates the need for separate supervised fine‑tuning and reinforcement learning objectives, allowing positive and negative offline completions, reference responses, and current and historical rollouts to share a common reward‑labeled format and replay buffer. Experiments on two model scales and four mathematical reasoning benchmarks show that CBPO, especially the CBPO‑Unified variant, outperforms baseline methods in avg@32 and pass@32 metrics, with historical rollouts providing additional gains.