cs.CL（2026-08-17）

📊 共 19 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) (14 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (14 篇)

#题目一句话要点标签🔗⭐
1 Closing the Affective Loop: Multimodal Speaker-Listener Emotion-Dynamics-Aware Empathetic Social Robots 提出AffectLoop以解决情感动态交互不足问题 multimodal
2 Architecture-Dependent Causal Transfer of Activation States Across Large Language Models 提出架构依赖的激活状态因果转移方法以优化LLM间通信 large language model
3 PolyDebate: A Game-Orchestrated Multimodal System for Debate Skills Practice and Evaluation 提出PolyDebate以解决传统辩论训练缺乏多模态支持的问题 multimodal
4 Semantic Bandits: In-Context Exploration-Exploitation is Biased by Semantic Priors 提出语义赌博者模型以解决LLM探索与利用的偏差问题 large language model
5 Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning 提出Palmyra x6以优化企业导向的智能代理任务 large language model
6 When Context Misleads: Intent-Guided Decoding for Robust Retrieval-Augmented Generation 提出意图引导解码以解决检索增强生成中的信任问题 large language model
7 HalluTracer: Hallucination Detection via Depth-Averaging Truth Signals 提出HalluTracer以解决语言模型幻觉检测问题 large language model
8 QUMem: Personalized Memory for Query-Conditioned User-State Inference in LLM Agents 提出QUMem以解决长交互历史中的用户状态推断问题 large language model
9 CAPO: Constraint-Aware Prompt Optimization for LLM Agents 提出CAPO以优化大型语言模型的系统提示 large language model
10 From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents 提出RUPA框架以解决LLM代理的不确定性量化问题 large language model
11 PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy 提出PCA引导的激活缩放以实现LLM的双向控制 large language model ✅
12 BabelSteering: Multilingual Safety Alignment via English Steering Vectors 提出BabelSteering以提升多语言安全性对齐问题 large language model
13 DSPrompt: Dynamic Soft Prompt Defense Against M-RAG Corruption 提出DSPrompt以解决M-RAG模型的对抗攻击问题 multimodal
14 Clause Encounters of the Third Kind: Can LLMs Replace Language Teachers? 评估大型语言模型在语言教学中的应用潜力 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
15 Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models 提出对比研究以揭示大语言模型在政策蒸馏中的双重泛化特性 distillation large language model
16 Mint-Agent: Introducing Finance-Native Agentic Foundation Models 提出Mint-Agent以解决金融智能的可靠性与执行性问题 distillation foundation model
17 Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning 提出步级在线蒸馏方法以解决现有蒸馏效果不足问题 distillation
18 Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning 提出ACA-RL框架以解决缺失前提推理问题 reinforcement learning
19 ClawGym II: Exploring Black-Box RL on Agent Harness 提出统一黑箱强化学习框架以优化复杂代理任务 reinforcement learning PPO

⬅️ 返回 cs.CL 首页 · 🏠 返回主页