cs.AI（2025-12-18）

📊 共 16 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) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (2) 支柱三：空间感知与语义 (Perception & Semantics) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 TOGGLE: Temporal Logic-Guided Large Language Model Compression for Edge 提出TOGGLE，通过时序逻辑引导LLM压缩，实现边缘设备高效部署。 large language model
2 How to Discover Knowledge for FutureG: Contextual RAG and LLM Prompting for O-RAN 提出Contextual RAG框架，提升O-RAN领域问答系统性能，无需微调LLM。 large language model chain-of-thought
3 HybridQuestion: Human-AI Collaboration for Identifying High-Impact Research Questions 提出HybridQuestion框架，结合人机协作识别高影响力研究问题。 large language model
4 PAACE: A Plan-Aware Automated Agent Context Engineering Framework PAACE：一种计划感知的自动化Agent上下文工程框架，提升Agent在复杂任务中的性能。 large language model
5 A Solver-in-the-Loop Framework for Improving LLMs on Answer Set Programming for Logic Puzzle Solving 提出ASP求解器在环框架，提升LLM在解答集编程逻辑谜题中的性能 large language model
6 Agent Tools Orchestration Leaks More: Dataset, Benchmark, and Mitigation 揭示Agent工具编排中的隐私泄露风险，并提出TOP-Bench基准与PEP缓解方法 large language model
7 Adaptation of Agentic AI 提出Agentic AI自适应框架，提升智能体性能、可靠性和泛化能力 foundation model
8 QuadSentinel: Sequent Safety for Machine-Checkable Control in Multi-agent Systems 提出QuadSentinel以解决多智能体系统中的安全控制问题 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
9 Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning 提出生成对抗推理器，通过对抗强化学习提升LLM的推理能力 reinforcement learning distillation reward shaping
10 Reinforcement Learning for Self-Improving Agent with Skill Library 提出基于强化学习的SAGE框架，提升LLM智能体在技能库应用中的自进化能力。 reinforcement learning large language model
11 Coordinated Anti-Jamming Resilience in Swarm Networks via Multi-Agent Reinforcement Learning 提出基于QMIX的多智能体强化学习方法，提升集群网络在反应式干扰下的抗干扰能力 reinforcement learning
12 Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows SGI-Bench：构建基于科学家工作流的科学通用智能评测基准 reinforcement learning multimodal

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
13 Realistic threat perception drives intergroup conflict: A causal, dynamic analysis using generative-agent simulations 利用生成式Agent模拟，揭示现实威胁感知驱动群体冲突的因果动态机制 manipulation large language model
14 Bots Don't Sit Still: A Longitudinal Study of Bot Behaviour Change, Temporal Drift, and Feature-Structure Evolution 揭示社交Bot行为随时间演变规律，为Bot检测系统设计提供依据 manipulation

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
15 Active Sensing Shapes Real-World Decision-Making through Dynamic Evidence Accumulation 提出基于动态证据累积的主动感知模型，用于解释真实驾驶场景中的决策过程 affordance
16 Distributional AGI Safety 提出分布式AGI安全框架，通过虚拟沙盒经济缓解群体风险。 affordance

⬅️ 返回 cs.AI 首页 · 🏠 返回主页