PAPER·July 25, 2026Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving SkillsarXiv
PAPER·June 3, 2026Harness-1: Reinforcement Learning for Search Agents with State-Externalizing HarnessesHugging Face Papers
TECH·June 2, 2026Turing Award winner Richard Sutton says pure generative AI can't do real scienceTHE DECODER
PAPER·June 2, 2026Harness-1: Reinforcement Learning for Search Agents with State-Externalizing HarnessesarXiv
PAPER·June 1, 2026LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric RewardsHugging Face Papers
SCIENCE·May 30, 2026Robots learn to recover from dangerous stair falls using a smart stabilising systemInteresting Engineering
PAPER·May 30, 2026LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric RewardsarXiv
PAPER·May 29, 2026Verifiable Rewards Beyond Math and Code: Lightweight Corpus-Grounded Process Supervision for Factual Question AnsweringHugging Face Papers
