Harness Self-Evolution for Long-Horizon Terminal Agents Paper • 2610.27435 • Published 30 days ago • 11
Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine Paper • 2610.22192 • Published Oct 15 • 31
ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents Paper • 2610.13395 • Published Oct 9 • 46
Self-Supervised Scaling of Terminal Environments for Scientific Domains Paper • 2610.02710 • Published Oct 2 • 12
Scaling Trajectories for Complex Tasks through Recursive Self-Rewrite Paper • 2610.02826 • Published Oct 2 • 38
FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders Paper • 2609.31620 • Published Sep 25 • 47
Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design Paper • 2609.22086 • Published Sep 18 • 30
T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks Paper • 2609.11042 • Published Sep 10 • 65
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations Paper • 2608.15930 • Published Aug 16 • 48
Recursive Synthesis for Long-Horizon Terminal Tasks Collection CC BY 4.0 datasets and SFT/RL checkpoints for recursive task synthesis; base-model and third-party terms still apply. • 6 items • Updated Aug 10 • 18
Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning Paper • 2607.18722 • Published Jul 21 • 35
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable Paper • 2607.13285 • Published Jul 14 • 113
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Paper • 2607.08964 • Published Jul 9 • 73
A Cookbook of 3D Vision: Data, Learning Paradigms, and Application Paper • 2606.04291 • Published Jun 2 • 6
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks Paper • 2604.20987 • Published Apr 22 • 20
Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills Paper • 2604.05333 • Published Apr 7 • 21
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data Paper • 2603.09206 • Published Mar 10 • 52