Raven
The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
- 6.3k
- Python
- Apache-2.0
- 22 h ago
The Harness of Harnesses • Super Agent: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.
RSI-Anything: Unlocking Recursive Self-Improvement with World Models
A curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.
The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".
A curated list for Self-Improvement in Foundation Model Based Agentic Systems.
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success but 65% Fewer Tokens
Self-improving code for any git repo: give it a measurable goal, a coding agent (Claude Code or Aider) proposes changes, the kernel scores them, keeps winners and rolls back failures. Open-source AlphaEvolve / FunSearch-style evolution loop, sandboxed, with an auditable ledger.
[EMNLP 2026] LightRSI is a modular runtime for lightly deploying recursive self-improvement loops in long-horizon LLM agents.
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
A recursive self-improvement (RSI) workflow that evolves both target agents (e.g., Pi and DeepSeek Harness) and the RSI system itself.
Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silicon.
Research report on recursive self-improvement with Agnes 3.0 Flash and Jev in Honor of Kings.
Coding-agent harness with recursive self-improvement (RSI), parallel Git worktree workers, skills and MCP extensions, and CLI and HTTP interfaces.
Guarded recursive self-improvement (RSI) for code agents with persistent e-LOND False Discovery Control (FDR) across 4 comprehensive studies.
Reinforcement learning model, used with transformers.
Reinforcement learning model, used with transformers.
Anonymous manuscript draft on recursive task-policy improvement through autonomous experience feedback in simulated robotic manipulation.