arXiv · Software Engineering· Yunbo Long, Guangya Hao, Yuhan Liu, Yiting Duan, Longyan Tan, Yunchen Long, Hao Wu·· 4 hr agoAI score35
编程智能体的自纠正应承载多少证据？面向自蒸馏的自适应 Dirichlet 证据
How Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-Distillation
AI brief
论文提出 Effective-Evidence Self-Distillation（EESD），把执行反馈中的转移支持与证据质量分开建模，用 Dirichlet 后验生成带不确定性惩罚的权重进行 KL 锚定的纠正学习。
Source: arXiv · Software Engineering · arxiv.org