cs.CL（2026-10-23）

📊 共 13 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 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1)

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

#题目一句话要点标签🔗⭐
1 The LLENS Platform for On-Premises Large Language Model Agents in a Japanese University Hospital: Development and Evaluation Study 提出LLENS平台以解决医院闭环网络中大型语言模型应用问题 large language model
2 The Punjabi Geet Toxicity Dataset (PGT-FG): Fine-Grained Multimodal Annotations for Toxic Content in Punjabi Songs 提出PGT-FG数据集以支持旁遮普歌曲中的毒性检测研究 multimodal
3 A Broader Look into MLLM's Retrieval Heads 提出优化检索头以提升多模态大语言模型的文档理解能力 large language model multimodal
4 How Much Do You Trust A Dog? Quantifying Hint-Following in Reasoning Language Models 量化推理语言模型中的提示跟随行为 large language model
5 "Not" is Not Lost in Translation: A Causal Analysis of Negation Representations in Multilingual LLMs 提出因果分析方法以研究多语言LLM中的否定表示 large language model
6 Natural Language Autoencoders Identify Without Explaining 提出自然语言自编码器以识别而非解释模型激活 chain-of-thought
7 PHYRD: A Living Benchmark for Reproducing and Extending Theoretical Physics Research 提出PHYRD基准以推动理论物理研究的复现与发现 large language model
8 SCI-AGENT-EXAM: Benchmarking Agents on Scientific Research Tasks 提出SCI-AGENT-EXAM以系统评估科学研究任务中的智能体能力 large language model ✅
9 From Promises to Accountability: Comparative AI Modeling and Visualization of Electoral Commitments in Nepali Political Texts 构建选举承诺挖掘系统以提升透明度与问责制 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
10 On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models 提出基于自生成问答对的自我训练框架以提升大语言模型性能 distillation privileged information large language model
11 SOPO: Socratic Guided Policy Optimization for Span-Level Hallucination Detection 提出SOPO以解决大语言模型的幻觉检测问题 reinforcement learning large language model ✅
12 Frontier-OPD: Discovering the Edge of Agent Capability and Teaching Agents to Go Beyond 提出Frontier-OPD以解决多轮智能体指导不足问题 teacher-student distillation

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
13 The Butterfly Defects: Tracing Cooperation in LLM Agent Networks 探讨LLM代理网络中的合作机制及其影响因素 dyadic interaction large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页