1
Causal Discovery in the Era of Agents
智能体时代如何发现因果关系？这篇最新论文给出前沿方法框架。
arXiv:2606.23608v1 Announce Type: new Abstract: Recent attempts to combine large language models (LLMs) with causal discovery ask models to infer pair…
2
Beyond Test-Time Memory: State-Space Optimal Control for LLM Reasoning
用状态空间最优控制超越测试时记忆，为大模型推理开辟全新范式
arXiv:2603.09221v2 Announce Type: replace Abstract: Associative memory has long underpinned the design of sequential models. Beyond recall, humans rea…
3
Search Self-play: Pushing the Frontier of Agent Capability without Supervision
无需人工标注，通过自主搜索对弈持续提升AI Agent能力极限，开辟无监督进化新方向
arXiv:2510.18821v3 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has become the mainstream technique for trai…