1
Tracing Agentic Failure from the Flow of Success
从成功流程中追溯智能体失败根源，揭示AI自主决策的脆弱性
arXiv:2607.12747v1 Announce Type: cross Abstract: Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajec…
2
Blog HN: Claude Code Making an Ass Out of You and Me
Claude Code在用户未及时回应时擅自假设并继续执行，暴露了AI工具自主决策边界的问题，值得所有依赖AI编码助手的人警惕。
I had an interesting experience today: Claude Code asked me a question that required consideration and, after I didn't reply within a short time frame…
3
Demonstration-Free Robotic Control via LLM Agents
无需人工演示，让LLM Agent自主控制机器人，智能决策新突破！
arXiv:2601.20334v2 Announce Type: replace-cross Abstract: Robotic manipulation has increasingly adopted vision-language-action (VLA) models, which ach…
4
Hierarchical Experimentalist Agents
提出分层实验者代理框架，通过层级结构提升AI自主实验与决策能力，为智能体研究开辟新路径。
arXiv:2606.29315v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to take actions in the real world and support hum…
5
RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments
新基准RetailBench登场，专门考验大模型智能体在真实零售场景中的长期自主决策与策略稳定性。
arXiv:2603.16453v2 Announce Type: replace Abstract: Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, ye…
6
AI 自主决策、无人工遥控，首届中学生人形机器人足球赛决出首站冠军
AI自主决策、无人工遥控，首届中学生人形机器人足球赛展现青少年科技实力与未来趋势。
IT之家 5 月 24 日消息，据央视新闻报道，5 月 23 日至 24 日，首届中学生人形机器人足球赛（北京海淀）总决赛于北京市清华附中落下帷幕。中央民族大学附属中学好耶战队在激烈竞争中脱颖而出，摘得桂冠；北京市海淀区教师进修学校附属实验中学极光队、人大附中航天城学校飞马队分别位列亚军和季军。 据…
7