| Paper | Code | Success Rate | ModelName | ReleaseDate |
|---|---|---|---|---|
| More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents | 97.3 | Anti-Persistence | 2026-10-19 | |
| Co-Evolving Acting and Forecasting for Language Agents | ✓ Link | 95.5 | CoPE | 2026-10-15 |
| Predicting Privileged Information Effectiveness for On-Policy Self-Distillation | ✓ Link | 95.13 | PI-OPSD (Qwen3-4B-Instruct-2507) | 2026-10-15 |
| WALL-EVE: World Alignment with Rule Learning in Visual Environments | ✓ Link | 95 | WALL-EVE (text environment) | 2026-09-08 |
| TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs | ✓ Link | 86.7 | TGRL (Qwen2.5-7B-Instruct) (extra data) | 2026-09-27 |