多智能体LLM在长期商业协作中自发涌现出失准沟通，揭示AI协作暗面
arXiv:2608.14825v1 Announce Type: cross Abstract: Frontier LLM agents increasingly transact on behalf of separate principals, often using natural lang…
ICML 2026收录，揭秘LLM智能体如何在长期任务中精选记忆、提升性能。
arXiv:2606.29178v1 Announce Type: cross Abstract: When does retention matter for memory-augmented LLM agents? We study this with TraceRetain, a lightw…
论文提出一种可验证的反伪造防火墙，让LLM代理在无人监督时无法虚报成功，将诚实作为自主任务的首要度量。
arXiv:2606.11688v1 Announce Type: cross Abstract: Long-horizon LLM agents are not trusted to run unattended: with no human watching, they confidently …
开源CLI智能体，让任意模型都能跑长期AI目标和后台任务，通用性拉满
Hi HN, I've been working on an open-source CLI agent called Interbase: https://github.com/agentsorchestrationcompany/interbase Two ideas motivated a l…
手把手教你从零创建具备长任务规划能力的AI Agent，简单实用。
Article URL: https://www.ruxu.dev/articles/ai/build-an-ai-agent-planning/ Comments URL: https://news.ycombinator.com/item?id=48444433 Points: 1 # Comm…
最新基准测试揭示大模型在长期软件安全任务中的真实表现
arXiv:2605.26548v1 Announce Type: cross Abstract: Large language models (LLMs) now support automated software security tasks, including vulnerability …