Pinned Loading
-
shepherd-agents/shepherd
shepherd-agents/shepherd PublicA runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-writ…
-
Human-Agent-Society/reef
Human-Agent-Society/reef PublicInfrastructure for continually self‑improving agents
-
MSR-Orchard/AutoEnvScaling
MSR-Orchard/AutoEnvScaling PublicAutoEnvScaling: Automating the Data Flywheel with Terminal Agents
-
spade-rl/spade
spade-rl/spade PublicSPADE: Self-Play in Adaptive Synthetic Executable Environments
-
CHATS-lab/verbalized-sampling
CHATS-lab/verbalized-sampling PublicVerbalized Sampling, a training-free prompting strategy to mitigate mode collapse in LLMs by requesting responses with probabilities. Achieves 2-3x diversity improvement while maintaining quality. …
-
TextArena/TextArena
TextArena/TextArena PublicA Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
If the problem persists, check the GitHub status page or contact support.