cs.AI（2026-01-16）

📊 共 14 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 Predicting Biased Human Decision-Making with Large Language Models in Conversational Settings 利用大型语言模型预测会话场景中人类决策偏差 large language model
2 Health Facility Location in Ethiopia: Leveraging LLMs to Integrate Expert Knowledge into Algorithmic Planning 提出LEG框架，融合专家知识与优化算法，解决埃塞俄比亚医疗设施选址问题 large language model
3 AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems AstroReason-Bench：评估统一智能体在异构空间规划问题中的规划能力 large language model
4 SD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented Generation SD-RAG：一种针对提示注入攻击的检索增强生成选择性披露框架 large language model
5 Do We Always Need Query-Level Workflows? Rethinking Agentic Workflow Generation for Multi-Agent Systems 提出SCALE框架以优化多智能体系统的工作流生成 large language model
6 ReCreate: Reasoning and Creating Domain Agents Driven by Experience 提出ReCreate框架以自动创建领域智能体 large language model
7 ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development ABC-Bench：真实后端开发中Agentic编码的基准测试 large language model ✅
8 AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts AgencyBench：百万Token真实世界上下文中的自主Agent基准测试 large language model ✅
9 Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents 提出一种隐蔽的、多轮的经济拒绝服务攻击，通过工具调用链放大LLM Agent的资源消耗。 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🔗⭐
10 TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech TANDEM：时序感知神经检测用于多模态仇恨言论识别，提升可解释性。 reinforcement learning multimodal TAMP
11 Cross-Modal Attention Network with Dual Graph Learning in Multimodal Recommendation 提出CRANE模型，通过递归跨模态注意力网络和双图学习增强多模态推荐效果。 contrastive learning multimodal
12 Policy-Based Deep Reinforcement Learning Hyperheuristics for Job-Shop Scheduling Problems 提出基于策略的深度强化学习超启发式算法，解决Job-Shop调度问题 reinforcement learning deep reinforcement learning
13 Learn Before Represent: Bridging Generative and Contrastive Learning for Domain-Specific LLM Embeddings LBR：桥接生成式与对比学习，提升领域特定LLM嵌入表示能力 representation learning contrastive learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 The Poisoned Apple Effect: Strategic Manipulation of Mediated Markets via Technology Expansion of AI Agents 研究AI技术扩展对市场均衡的影响，揭示“毒苹果效应”及监管挑战 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页