← Back to radar
Observation record / arXiv · 人工智能
Evolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents
First seen 10/17, 04:20 · Last observed 10/18, 10:21 · Source data is current
Read the original source ↗Title-based outlineEvolving Together, Failing Apart: The Skill-Policy Co-evolution Trap in Self-Improving Agents
Why it mattersResearch metadata links to papers and authors. Read the original for conclusions; publication order is not impact.
30 minutesRank movement—
Building history
1 hourRank movement—
Building history
24 hoursRank movement—
Building history
Publication position history
6 observationsPublication feed in source order. Position changes do not count as heat or momentum.
arXiv metadata CC0; papers retain individual licenses· Author Yujie Feng, Xiaobin Wang, Jinluan Yang, Xiaonan Shi, Pengjun Xie, Philip S. Yu, Xiaoming Wu, Jieping
View original observation times and ranks
| Observation time (Beijing) | Source position |
|---|---|
| 10/18, 10:21 | 17 |
| 10/18, 04:21 | 17 |
| 10/17, 22:21 | 17 |
| 10/17, 16:21 | 17 |
| 10/17, 10:20 | 17 |
| 10/17, 04:20 | 17 |
Daily aggregate history
| 日期 | Best daily position | Last daily position | Observations |
|---|---|---|---|
| 2026-10-17 | 17 | 17 | 4 |
| 2026-10-18 | 17 | 17 | 2 |