Topic
Reinforcement Learning with Verifiable Rewards uses outcomes that can be checked by programs, tests, simulators, or formal rules. Math, code, and tool-use tasks are common examples. RLVR can make feedback cheaper and more scalable than human preference labeling, but only where the verifier captures the behavior that matters and resists reward gaming.
Verifiable outcomes
Programmatic graders
Reward hacking
Reasoning traces
Latest research
Qiancheng Zhou
A controlled study of where reasoning diversity disappears during RLVR, distinguishing failure to initiate a solution family from failure to execute it after the first reasoning choice.
Xingyu Shen
A method for preserving reasoning diversity during RLVR by conditioning the target model on partial trajectories produced by a smaller, weaker model.
Steven Byrnes
A community synthesis linking four training signals—imitation, human approval, automatic verifiers, and LLM judges—to distinct classes of observed or hypothesized alignment failure.
Fiora Starlight
A LessWrong proposal to let policies report exploitable RLVR environment bugs after a rollout, reward high-quality verified reports, and use them to patch the training environment.
Steven Byrnes
A community argument that RLVR is operationally important but that most language-model knowledge and available reasoning strategies still originate in pretraining and supervised imitation.
Yufei Li
A production-oriented technical report on a generative reasoning re-ranker trained with semantic-ID mid-training, teacher-trace distillation, on-policy distillation, and reinforcement learning from verifiable ranking rewards.
CarolusRenniusVitellius
A concise reading map of weight-level and behavioral evidence on whether RLVR mainly reweights existing capabilities or creates new reasoning mechanisms.
Zichen Liu
A controlled examination of R1-Zero-style reinforcement learning that separates robust training effects from claims that are sensitive to setup, reward design, and evaluation choices.
Weihao Zeng
An empirical study of reinforcement learning directly from open base models, focused on making zero-RL experiments easier to reproduce and compare across model families.
DAPO Team
DAPO presents an open reinforcement-learning system and a collection of training interventions aimed at improving large-scale reasoning optimization.
DeepSeek-AI
DeepSeek-R1 documents a reasoning-model training pipeline centered on reinforcement learning, including a zero-style RL stage and a staged route that combines supervised data with RL.
Kimi Team
A technical report on scaling multimodal language-model reinforcement learning with long-context training, policy optimization, and data-selection strategies.
DeepSeek-AI
DeepSeekMath combines a math-focused data pipeline with supervised fine-tuning and reinforcement learning, and introduces Group Relative Policy Optimization.
Princeton University
SWE-bench turns real GitHub issues and repository states into tasks for evaluating whether language models can produce working software patches.
OpenAI
A comparison of outcome supervision and process supervision for mathematical reasoning, centered on whether feedback should evaluate only the final answer or intermediate steps as well.