cs.AI（2026-07-13）

📊 共 21 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) (17 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱六：视频提取与匹配 (Video Extraction) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models	提出MAGIC以解决多场景导航生成中的一致性与可达性问题	large language model multimodal	✅
2	Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought	提出CAID以解决链式推理中的潜在低效问题	large language model chain-of-thought
3	Reproducing human biases in route choice using large language models: Toward scalable behavioral modeling	利用大型语言模型重现人类路线选择中的偏见	large language model
4	Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns	提出多模态语言模型以重现失语症患者的命名错误模式	multimodal
5	The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning	提出TRACE框架以增强多模态推理的证据基础	multimodal
6	OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping	提出OS-Pruner以解决大语言模型推理链冗余问题	large language model chain-of-thought
7	StructAgent: Harness Long-horizon Digital Agents with Unified Causal Structure	提出StructAgent以解决长时间任务执行中的状态管理问题	large language model
8	A Formal Hierarchical Architecture for Agentic Orchestration with Stack-Based Execution and Lazy Discovery	提出层次化架构以解决LLM代理工具选择瓶颈问题	large language model
9	Playful AI in Professional Email: A Field Experiment on Tone and Recipient Engagement	探讨AI辅助写作对职场沟通的情感影响	large language model
10	Think Through a Bottleneck: Hourglass Reasoning for Rigorous Induction	提出Hourglass推理以解决少样本归纳推理问题	large language model
11	HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference	提出HCRMap以解决3.5D MoE推理中的专家热度不均问题	large language model
12	Omni-Decision: A Progressive Evidence-State Agent System for Omni-Modal QA	提出Omni-Decision以解决多模态QA中的证据追踪问题	multimodal
13	Verifier-Guided Twelve-Tone Composition: A Generate-Verify-Repair Harness for Symbolic Music Generation	提出神经符号框架以解决十二音音乐生成中的一致性问题	large language model
14	The Paternalistic Filter: Epistemic Injustice and Differential Refusal in LLM-Mediated History Education for Marginalized Romanian Students	提出父权主义过滤器以解决边缘化学生的教育不平等问题	large language model
15	Multi-Agent LLMs Fail to Explore Each Other	提出MACE框架以解决多智能体探索不足问题	large language model	✅
16	AMT-X: Phase-Structured Multi-Turn Red-Teaming with Checklist-Gated Evaluation	提出AMT-X框架以解决多轮攻击评估不足问题	large language model
17	BackendForge: Benchmarking Agentic End-to-End Code Generation with Backend Services	提出BackendForge以评估智能代码生成的可部署性与正确性	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	🔗	⭐
18	SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning	提出SVR-R1以解决多模态推理中的自我验证问题	reinforcement learning multimodal
19	Auditing the Risk Claims of Distributional Reinforcement Learning	审计分布式强化学习的风险声明以验证其真实性	reinforcement learning
20	DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs	提出DeepBias框架以深入探测LVLM中的社会偏见	DPO direct preference optimization

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
21	AdvNav: Behavior-Guided Black-Box Adversarial Attacks on Vision-Language Navigation	提出AdvNav以解决视觉语言导航中的黑箱对抗攻击问题	first-person view embodied AI VLN

⬅️ 返回 cs.AI 首页 · 🏠 返回主页