cs.AI（2026-07-06）

📊 共 20 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) (15 🔗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) (15 篇)

#题目一句话要点标签🔗⭐
1 Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards 提出Dashboard2Code以解决交互式仪表板生成问题 large language model multimodal
2 Detecting Answer-Driven Reasoning in LLM-Based Educational Tutors via Truncated Chain-of-Thought Auditing 提出TRACE方法以解决LLM教育辅导中的答案驱动推理问题 large language model chain-of-thought
3 Selective Disclosure Watermarking for Large Language Models 提出分层词汇路由水印技术以解决选择性披露问题 large language model ✅
4 ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions 提出ProPS框架以生成自然语言条件下的说话人嵌入分布 language conditioned
5 AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments 提出AgentGym2以解决现实环境中LLM代理评估不足的问题 large language model
6 TacReasoner: A Dynamic Tactile-Language Framework for Interactive Reasoning in Real-World Scenarios 提出TacReasoner以解决动态触觉信号推理问题 foundation model multimodal chain-of-thought
7 Toward Trustworthy Large Language Model Agents in Healthcare 提出CareConnect以解决医疗预约调度问题 large language model ✅
8 Heaviside Continuity of Rolling Coefficients for Eliminating Epistemic Entropy in Large Language Models 提出HCRC框架以消除大型语言模型中的认知熵问题 large language model
9 ASSEMCAD: Production-Ready CAD Assembly Generation from Natural Language 提出AssemCAD以解决生产就绪的CAD装配生成问题 large language model foundation model
10 TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction 提出TACTIC-KG以解决网络威胁情报知识图谱构建问题 large language model
11 LLM for the development of FCM 利用局部大语言模型开发模糊认知图 large language model
12 The Changing Role of Symbolic Methods in Artificial Intelligence 提出压缩原则以重新审视符号方法在人工智能中的角色 foundation model
13 DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation 提出DSpark以解决大语言模型推理效率问题 large language model
14 LLM-Based Test Oracles: Source-of-Authority Taxonomy -- A Systematic Literature Review 提出基于LLM的测试预言机权威来源分类以解决信任问题 large language model
15 Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses 提出FARMA攻击与SENTINEL防御以保护LLM代理的推理历史 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🔗⭐
16 MoP-JEPA: Hard-Assigned Predictor Mixtures for Stochastic JEPA World Models 提出MoP-JEPA以解决随机环境下预测失效问题 world model world models JEPA
17 CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs 提出CARL框架以解决LLMs任务约束违反问题 reinforcement learning large language model
18 Rethinking On-Policy Self-Distillation for Thinking Models 重新思考基于策略的自蒸馏以提升思维模型性能 distillation privileged information
19 STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training 提出STAPO以解决长任务中轨迹忽视问题 reinforcement 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🔗⭐
20 SovereignPA-Bench: Evaluating User-Owned Personal Agents under Evolving Intent, Platform Mediation, and Consent Constraints 提出SovereignPA-Bench以评估用户拥有的个人代理在隐私与同意约束下的表现 manipulation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页