The authors model deployment as a stream of tasks in which feedback becomes available only after each task finishes.
Safety systems that learn from runtime experience protect LLM agents
SafeCoEvo combines rapidly updated safety instructions with a slower-trained guard to improve decisions on unseen tasks.
Chinese Tech
Yu Cheng · Yongkang Hu · Shuaijie Ma · Zhihang Lin · Weicheng Meng · Jingyang Qiao · +9 more
East China Normal University · Shanghai Innovation Institute · Xiamen University · Harbin Institute of Technology · University College London
Research Digest··2 min read
Cheng et al.
Why this paper
From Huawei Noah’s Ark Lab, UK and 7 others
In one line
SafeCoEvo co-evolves an external safety harness and guard at test time, cutting unsafe outcomes by 10.05% and raising task success by 12.15% over the strongest baseline.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors (2 noted)
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§