| 2026-10-14 | 2610.14709 | Vela: User Behavior as Supervision Sparks LLM Intelligence | Yang Xiao et al. | arXiv | 85 | |
| 2026-09-30 | 2609.35954 | ROSS: Relearning from Self-Generated Rollouts through Selective Supervision | Zhiwei Zhang et al. | arXiv | 34 | |
| 2026-09-29 | 2609.33665 | CompoWorld: Compositional Environment Scaling for General Agents | Xiao-Wen Yang et al. | arXiv | 40 | |
| 2026-09-29 | 2609.33772 | Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents | Weiyi Xu et al. | arXiv | 36 | |
| 2026-09-29 | 2609.33642 | Learning to Learn from Context: Synthetic Training from Perturbed Public Documents | Haoyi Wu et al. | arXiv | 31 | |
| 2026-09-24 | 2609.26355 | PACT: From Credit Assignment to Critic Alignment | Jiayan Fu et al. | arXiv | 28 | |
| 2026-09-08 | 2609.02998 | Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation | Zhiwei Zhang et al. | arXiv | 16 | |
| 2026-09-07 | 2609.04304 | Iris: Climbing to the Search Frontier | Ziyuan Liu et al. | arXiv | 50 | |
| 2026-08-28 | 2608.26530 | PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents | Yang Xiao et al. | arXiv | 36 | |
| 2026-08-27 | 2608.24987 | D^3-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation | Zechen Sun et al. | arXiv | 28 | |