cs.CL（2026-10-01）

📊 共 35 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (29 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗2) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (29 篇)

#题目一句话要点标签🔗⭐
1 Which LLM to pick? Online Active Model Selection for Large Language Models 提出ONLINE LLM PICKER以解决在线大语言模型选择问题 large language model
2 A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined 构建临床推理评估标准以提升大语言模型的临床应用能力 large language model
3 Counting and Min-Cost Encoding for Tokenization in Large Language Models 提出CNF-MCE方法以提高大语言模型的编码效率 large language model
4 A Citation-Grounded Benchmark for Trustworthy Earnings Call Transcript Analysis with Large Language Models 提出一种基于引用的基准以解决财报分析中的可信度问题 large language model
5 Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations 提出统一框架以解决大语言模型任务适应性问题 large language model
6 Can LLMs Reliably Annotate Bioassay Metadata to Improve Data Readiness? 利用大型语言模型提升生物测定元数据的注释可靠性 large language model foundation model
7 Beyond Leaderboards: Tokenomics of Agentic Small Language Model Ensembles 提出小型语言模型集成的经济学评估方法以提升智能体性能 large language model instruction following
8 From Knowledge Access to Source Learning: Developing Source-Specific Competence 提出SourceLearn以解决源知识理解不足问题 large language model
9 Scalable, Transferable Meta-network for Data Selection Requires a Different Loss (and Why the Obvious Choice is Problematic) 提出可扩展的TESS框架以解决数据选择问题 large language model
10 Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities 提出通用字节级编码以减少跨脚本令牌预算差异 large language model
11 Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs 提出稳定性意识的泛化目标以评估大型语言模型的泛化能力 large language model
12 When Does a Second Model Help? Cross-Model Review in LLM Verification 提出跨模型审查方法以提升大型语言模型的验证效果 large language model
13 It Takes Workflows to Evolve Better Workflows 提出FloWright以优化多代理工作流的生成与执行 large language model ✅
14 LLM2Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them 提出LLM2Jev框架以优化大语言模型的决策能力 multimodal
15 Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation 提出系统化方法评估大型语言模型的创意新颖性 large language model
16 Acmite: Mitigating Gender Bias in LLMs through Concept-Guided Mutual Information 提出Acmite以解决大型语言模型中的性别偏见问题 large language model
17 Yo-ByT5: Efficient and High-Fidelity Diacritic Restoration for Yorùbá 提出Yo-ByT5以解决约鲁巴语的音调符号恢复问题 large language model
18 How the Audit Rule Shapes Faithful Factor Explanations in LLMs 提出报告独立审计以解决LLM因果解释的真实度问题 large language model
19 Auditing Web Agent Evaluation on WebArena-Lite: Human Review of Outcomes and Trajectories 提出人类审查机制以提升Web代理评估的准确性 large language model
20 Does AI-Generated Scientific Text Follow Human Argumentation Patterns? A CARS-Based Comparison of Research Article Introductions 基于CARS模型比较AI生成与人类撰写的科学文本 large language model
21 Evaluating the Robustness of Japanese LLMs to IME-Related and Typographical Errors 评估日本LLM对输入法和打字错误的鲁棒性 large language model
22 LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded Evidence 提出LawCompass以解决复杂法律任务的研究需求 large language model
23 Role-aware Heuristic Episodic Attention for Conversational LLMs 提出角色感知启发式情节注意力以解决对话LLM的上下文衰减问题 large language model
24 ReHoPER: Receding-Horizon Planning for Enhanced Reasoning 提出ReHoPER以增强大语言模型的推理能力 large language model
25 Evaluating Multi-Dimensional Generalization of Large Language Models in Temporal Extraction Tasks 评估大型语言模型在时间提取任务中的多维泛化能力 large language model
26 Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities 提出通用字节级编码以解决跨脚本令牌预算差异问题 large language model
27 Counterexample Generation via Per-Theorem Symbolic Verifiers: When Imitation Hurts and Reinforcement Repairs 通过定理符号验证器生成反例以解决伪命题问题 large language model ✅
28 SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents 提出SEDIMA以解决进化搜索代理的记忆不足问题 large language model
29 HakemBench: A Turkish Benchmark of Typed Decisions 提出HakemBench基准以评估土耳其语言决策模型的性能 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🔗⭐
30 My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning 提出FAULT以解决长时程强化学习中的信用分配问题 reinforcement learning large language model
31 Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents 提出Mem++以解决组织工作中的长期记忆问题 distillation large language model ✅
32 Probe with Participation Trophies: Random-Reward RL as a Probe of LLM Capability 提出随机奖励强化学习以探测大语言模型能力 reinforcement learning large language model
33 Distilling Directional Verification 提出方向性标签蒸馏以改善知识转移效率 distillation large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
34 The Persona Is Still There, but Who Is Speaking? Latent Identity Reversion in Persistent AI Agents 探讨持久AI代理中的身份逆转现象 manipulation
35 Evaluating and Improving the Robustness of Large Language Models to Input Sequence Variations 提出评估与提升大语言模型对输入序列变异的鲁棒性的方法 manipulation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页