Topic
Rewards translate outcomes and preferences into the signal used to improve a policy. They may come from humans, learned reward models, AI judges, tests, or executable verifiers. This topic follows how reward signals scale, where they fail, and how evaluation can detect proxy optimization before it becomes a production problem.
Reward models
AI feedback
Process supervision
Verifier calibration
Latest research
Jingxiao Yang
A work-in-progress study of long-horizon agent reinforcement learning that uses privileged process supervision to redistribute verified trajectory-level credit across executable actions.
Z.ai
An official GLM-5.3 release note describing a post-training-only update on the same base model as GLM-5.2, with expanded executable environments for complex coding, security, and long-horizon professional workflows.
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.
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.
Z.ai
An official release of the 750B-A40B GLM-5.2 model, combining a one-million-token context, IndexShare sparse-attention reuse, and larger-scale agentic reinforcement learning for long-horizon tasks.
MiniMax
An official release of MiniMax-M3, a natively multimodal sparse model with about 428B total and 23B active parameters, a one-million-token context window, and agent-oriented coding and cowork capabilities.
MiniMax
A technical report on the MiniMax-M2 family, pairing a 229.9B-parameter sparse MoE with agent-generated, verifiable trajectories and Forge, a scalable reinforcement-learning system for long-horizon agents.
Meta FAIR
This work studies language models that generate candidate responses and also provide the preference signal used to improve subsequent iterations.
NVIDIA
Eureka uses a code-capable language model to propose and iteratively improve executable reward functions for reinforcement-learning tasks.
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.
Anthropic
Constitutional AI uses written principles and model-generated critiques and preferences to reduce direct dependence on human harmlessness labels during alignment training.
OpenAI
An empirical study of how optimizing against a learned reward model can eventually reduce performance under a higher-quality reference signal.
OpenAI
A large-scale study of training summarization models from human comparisons using reward modeling and reinforcement learning.
OpenAI
A foundational study of learning a reward model from pairwise human preferences and using that learned reward to train an RL agent.