Vela: User Behavior as Supervision Sparks LLM Intelligence Paper • 2610.14709 • Published 10 days ago • 88
ROSS: Relearning from Self-Generated Rollouts through Selective Supervision Paper • 2609.35954 • Published 22 days ago • 54
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents Paper • 2609.33642 • Published 23 days ago • 35
CompoWorld: Compositional Environment Scaling for General Agents Paper • 2609.33665 • Published 23 days ago • 42
Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents Paper • 2609.33772 • Published 23 days ago • 36
Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation Paper • 2609.02998 • Published Sep 2 • 19
D^3-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation Paper • 2608.24987 • Published Aug 25 • 28
PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents Paper • 2608.26530 • Published Aug 27 • 37
TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios Paper • 2602.01675 • Published Feb 2 • 10
Agent Laboratory: Using LLM Agents as Research Assistants Paper • 2501.04227 • Published Jan 8, 2025 • 96