| 2026-11-19 | 2611.21553 | BLIP-Live: Balancing Timeliness & Firing Precision in Proactive Streaming Video Agents | Kanchana Ranasinghe et al. | arXiv | 9 | |
| 2026-10-20 | 2610.22324 | Training Reasoning Models to Generate Diverse Scientific Ideas | Manya Wadhwa et al. | arXiv | 6 | |
| 2026-10-16 | 2610.06829 | CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling | Yifan Zhang et al. | arXiv | 6 | |
| 2026-10-13 | 2610.02740 | Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps | Jiaxin Zhang et al. | arXiv | 9 | |
| 2026-10-09 | 2609.33987 | Opera: A Verbal Critic Framework for Long-horizon Coding Agents | Kai Mei et al. | arXiv | 13 | |
| 2026-10-08 | 2610.08077 | Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight | Haoxiang Zhang et al. | arXiv | 172 | |
| 2026-09-24 | 2609.27334 | Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents | Yefan Zhou et al. | arXiv | 54 | |
| 2026-09-17 | 2609.14306 | Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training | Shrey Pandit et al. | arXiv | 18 | |
| 2026-09-09 | 2609.04280 | EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness? | Zixuan Ke et al. | arXiv | 29 | |
| 2026-09-07 | 2609.05295 | RISE: Recursive Improvement via Self-Extrapolating Policy Distillation | Yang Li et al. | arXiv | 18 | |
| 2026-09-04 | 2609.03430 | Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning | Heng Wang et al. | arXiv | 73 | |
| 2026-08-14 | 2608.07545 | DarwinX: Evolving Agent Harnesses Through Natural Selection | Yifan Zhang et al. | arXiv | 97 | |
| 2026-07-28 | 2607.22798 | StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents | Yan Yang et al. | arXiv | 62 | |
| 2026-07-14 | 2607.11862 | Evidence-Backed Video Question Answering | Shijie Wang et al. | arXiv | 4 | |
| 2026-05-21 | 2605.15113 | Learning from Language Feedback via Variational Policy Distillation | Yang Li et al. | arXiv | 10 | |