2 papers
cs.LG2026
HarnessEvolve: Learning from Reference Trajectories for Reliable Agent Self-Evolution
Wen Jiang, Mingmin Chu, Yimeng Tian +6
Self-evolving agents advance toward autonomy by optimizing their harness---prompts, skills, tools, and execution logic---based on environmental feedback. This paradigm, however, is…
cs.LG2026
FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery
Yue Li, Mingmin Chu, Xilei Yang +5
Federated learning (FL) enables collaborative model training without centralizing raw data, but privacy regulations such as the right to be forgotten require FL systems to remove t…