Amarsaikhan Batjargal, Noriko Tomuro · 2026 · arXiv
DOI: 10.48550/arXiv.2610.26416 · open-access PDF
可验证的奖励增强学习(RLVR)特别适合代码生成,因为生成的程序可以通过执行客观地评估。执行还提供可作为额外监督的行为信息。最初为推理任务提出的协同政策和奖励合作发展框架(SPARK)通过回收培训部署和其评估结果来利用这一想法,以训练模型,不仅可以生成解决方案,还可以评估和改进它们。
Machine translation (Meta M2M100); the English original follows.
Reinforcement learning with verifiable rewards (RLVR) is particularly well suited to code generation because generated programs can be objectively evaluated through execution. Execution also provides behavioral information that can be reused as additional supervision. The Synergistic Policy and Reward Co-Evolving Framework (SPARK), originally proposed for reasoning tasks, exploits this idea by recycling training rollouts and their evaluation results to train a model not only to generate solutions but also to evaluate and improve them. We investigate whether this policy-reward co-evolution appr
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26416, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange