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
Fin.ai
The paper probes whether reference-conditioned self-distillation actually locates and corrects reasoning errors. Generating a critique before scoring gives more error-specific feedback in the tested models, and small Knights & Knaves training experiments improve with a critique-conditioned term. Every critique has access to a reference solution.
Dalian Maritime University
A GSM8K study separates current-policy sample selection from progression between difficulty bands in GRPO. With Qwen2.5-1.5B-Instruct and LoRA, a staged curriculum reaching moderately harder problems improves test accuracy over persistent medium-difficulty selection, while a further difficulty increase reverses the gain across three seeds.
Alibaba Group
Zero-Sum Calibrated Policy Optimization (ZCPO) puts reference-policy drift into group-relative update coefficients instead of adding an independent KL loss. The paper analyzes seven potential KL–reward mismatches and reports improved math and long-context performance in its tested configurations.
Harbin Institute of Technology (Shenzhen)
GRPODropout selectively excludes high-probability positive-advantage rollouts from GRPO updates, then recenters retained advantages using old-policy probability weights. With the same generation budget, experiments on Qwen3 models report higher average benchmark accuracy and less entropy collapse than standard GRPO.
Li, Shuyue Stella
Verifiable Visual Rewards derives image prompts and deterministic constraint checks from the same geometric scene specification. Flow-GRPO training on simple synthetic scenes improves instruction following in Stable Diffusion 3.5 Medium and transfers to natural-image prompts, with measurable tradeoffs.
Michael Noukhovitch
Never Give Up reallocates rollout compute toward hard problems by quickly filtering easy groups and repeatedly sampling unsolved ones. The study links this adaptive allocation to better learning signals on difficult mathematical and coding tasks.
Yang Li
RISE constructs a distillation teacher by extrapolating a model’s own RLVR training trajectory. Alternating reward-based updates with token-level distillation improves the tested reasoning and agent policies while reusing their sampled rollouts.
Tsinghua University
An empirical study of how prompt difficulty and reasoning length affect on-policy distillation. Eight selected hard math problems approach the performance of a 17K-problem baseline, while repeated rollout generation and dense teacher supervision remain part of training.
New York University
An empirical study of how to combine on-policy distillation with RLVR. Training with distillation first and RL second produces strong logic-reasoning gains, while the advantage over the strongest alternatives is less decisive on math.
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.