Topic · 31 recaps

Reinforcement Learning

Learning from reward signals through trial and interaction with an environment. Spans classic RL, RLHF, and modern post-training methods for language and agent models.

Sort

Newest

J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data

Evaluation · Aug 27

StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing

Agents · Aug 25

Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs

Multimodal · Aug 20

EnvHarness: Awakening Static Worlds for Agent Learning

Agents · Aug 20

DART-SD: Diamond-topology Aware Retrieval and Tuning for Self-Distillation of Multi-Turn Tool-Calling Agents

Agents · Aug 19

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Reasoning · Aug 17

Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design

Agents · Aug 10

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Agents · Aug 6

Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning

Multimodal · Aug 6

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

LLM Training · Aug 6