cs.CL（2026-06-11）

📊 共 23 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) (17 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (6)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#题目一句话要点标签🔗⭐
1 NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning 提出NTS-CoT以解决LLM新闻时间线摘要中的幻觉问题 chain-of-thought
2 Beyond Uniform Tokens: Adaptive Compression for Time Series Language Models 提出自适应压缩方法以提高时间序列语言模型的效率 large language model foundation model
3 MemRefine: LLM-Guided Compression for Long-Term Agent Memory 提出MemRefine以解决长时间交互中的记忆管理问题 large language model
4 IVIE: A Neuro-symbolic Approach to Incremental and Validated Generation of Interactive Fiction Worlds 提出IVIE以解决互动小说世界生成中的创意与一致性问题 large language model
5 G-Long: Graph-Enhanced Memory Management for Efficient Long-Term Dialogue Agents 提出G-Long以解决长时间对话一致性问题 large language model
6 LLMs Contain Multitudes: How Deployment Context Reshapes Model-Level Preferences and Values 提出部署上下文影响模型偏好的研究方法 large language model
7 DLawBench: Evaluating LLMs Through Multi-Turn Legal Consultation 提出DLawBench以评估大型语言模型在法律咨询中的表现 large language model
8 EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments 提出EvoArena与EvoMem以解决动态环境下LLM代理的记忆演变问题 large language model
9 Influcoder: Distilling Decoders' Gradient Influence Rankings into an Encoder for Data Attribution 提出Influcoder以解决大规模数据归因问题 large language model
10 Which Models Perform Better in Inheritance Reasoning? 比较商业与开源模型在继承推理中的表现 large language model
11 RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue 提出RogueAI以检测对话中的AI欺骗行为 large language model
12 When Similar Means Different: Evaluating LLMs on Arabic--Hebrew Cognates 提出SemCog Bench以评估阿拉伯语-希伯来语同源词的语义理解能力 large language model
13 EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge 提出EvoBrowseComp以解决静态基准测试的局限性 large language model
14 Polar: A Benchmark for Evaluating Political Bias in LLMs 提出Polar基准以评估大型语言模型中的政治偏见 large language model
15 PRISM: Prosody-Integrated Multi-Agent Reasoning Framework for Empathetic Spoken Dialogue 提出PRISM框架以解决同情心对话系统中的情感表达问题 large language model ✅
16 SafeLLM: Extraction as a Hallucination-Resistant Alternative to Rewriting in Safety-Critical Settings 提出SafeLLM以解决安全关键环境中的重写问题 large language model
17 GENIE: A Fine-Grained Measure for Novelty 提出GENIE以细致衡量生成内容的新颖性 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#题目一句话要点标签🔗⭐
18 LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories 提出LabVLA以解决科学实验中AI执行能力不足的问题 flow matching vision-language-action VLA
19 ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages 提出ArogyaSutra以解决多模态医疗推理的语言障碍问题 distillation large language model multimodal
20 Direct Preference Optimization for Chatbot Fine-Tuning: An Empirical Study 提出直接偏好优化方法以简化聊天机器人微调过程 reinforcement learning DPO direct preference optimization
21 From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent 提出ProReviewer以解决科学同行评审中的主动调查问题 reinforcement learning large language model
22 SENTINEL: Failure-Driven Reinforcement Learning for Training Tool-Using Language Model Agents 提出SENTINEL框架以解决工具使用语言模型代理的训练挑战 reinforcement learning
23 Learning to Reason by Analogy via Retrieval-Augmented Reinforcement Fine-Tuning 提出基于检索增强的强化微调方法以解决复杂推理问题 distillation reward design

⬅️ 返回 cs.CL 首页 · 🏠 返回主页