RSI-Exam: Measuring Recursive Self-Improvement on Long-Horizon, Executable Research Tasks · Discord https://discord.gg/FBzhepyE
Like aiming-lab/RSI-Exam, 0 likes 0 Bookmark aiming-lab/RSI-Exam, 0 bookmarks 0 RSI Bench is an ongoing effort to evaluate whether AI agents can develop the capabilities required to advance AI R&D.
Like scaleapi/rsi-benchmark, 0 likes 0 Bookmark scaleapi/rsi-benchmark, 0 bookmarks 0 🐕 Beagle is designed to be the unified platform for the broader Recursive Self-Improvement (RSI) ecosystem. Think of it as Hugging Face Trainer for agent evolution. Its efficient rollout engine enables evaluation and evolution at scale across different agents, datasets, benchmarks, and evolution methods.
Like SalesforceAIResearch/Beagle, 0 likes 0 Bookmark SalesforceAIResearch/Beagle, 0 bookmarks 0 A Unified Framework for Efficient RSI Research
Like RUC-NLPIR/FlashRSI, 0 likes 0 Bookmark RUC-NLPIR/FlashRSI, 0 bookmarks 0 a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
Like greyhaven-ai/autocontext, 0 likes 0 Bookmark greyhaven-ai/autocontext, 0 bookmarks 0 General agent evaluation framework
Like Exgentic/exgentic, 0 likes 0 Bookmark Exgentic/exgentic, 0 bookmarks 0 Unofficial distillation and executable skill for Stanford CS329A Self-Improving AI Agents
Like yusenthebot/stanford-ai-agent-skill, 0 likes 0 Bookmark yusenthebot/stanford-ai-agent-skill, 0 bookmarks 0 Recursive Self-Improvement for AI agents and models, helping your agents self-improve with every run
Like raia-live/amfs, 0 likes 0 Bookmark raia-live/amfs, 0 bookmarks 0 Bring your own agent and build a self-improving agentic system. Automatically mine failures, optimize the agent harness, and gate against regressions.
Like neosigmaai/auto-harness, 0 likes 0 Bookmark neosigmaai/auto-harness, 0 bookmarks 0 
