Trace: Capability-Targeted Agentic Trainingscalingintelligence.stanford.edu1 ポイント·投稿者 mbeissinger·3 か月前·0 コメント
Meta-Harness: automated search over task-specific model harnessesgithub.com1 ポイント·投稿者 mbeissinger·3 か月前·0 コメント
Meta-Harness: End-to-End Optimization of Model Harnessesyoonholee.com2 ポイント·投稿者 mbeissinger·4 か月前·0 コメント
mbeissinger·昨年·議論You might want to check out the conversational chunking from this paper:On Memory Construction and Retrieval for Personalized Conversational Agents https://arxiv.org/abs/2502.05589
On Memory Construction and Retrieval for Personalized Conversational Agents https://arxiv.org/abs/2502.05589