cs.AI（2025-09-28）

📊 共 7 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
1 Improving the Efficiency of LLM Agent Systems through Trajectory Reduction AgentDiet：通过轨迹缩减提升LLM Agent系统效率，降低计算成本。 large language model
2 Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence 揭示LLM辅助网络威胁情报的脆弱性，提出针对性分析方法 large language model
3 Benchmarking LLM-Assisted Blue Teaming via Standardized Threat Hunting CyberTeam：通过标准化威胁狩猎基准评估LLM在蓝队行动中的辅助能力 large language model
4 Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment PrefCleanBench：首个LLM对齐偏好数据清洗基准，提升奖励模型质量 large language model ✅
5 Beyond the Strongest LLM: Multi-Turn Multi-Agent Orchestration vs. Single LLMs on Benchmarks 多智能体协同超越最强LLM：多轮交互在基准测试中优于单一大模型 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
6 Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning 提出PASS框架，利用强化学习和形式化描述提升LLM提示越狱攻击的隐蔽性和有效性 reinforcement learning large language model
7 Reasoning Scaffolding: Distilling the Flow of Thought from LLMs 提出推理支架(Reasoning Scaffolding)框架，提升小模型推理能力和逻辑一致性。 distillation large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页