cs.AI（2026-09-22）

📊 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) (15) 支柱二：RL算法与架构 (RL & Architecture) (6) 支柱八：物理动画 (Physics-based Animation) (1) 支柱一：机器人控制 (Robot Control) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	ChatT2: An Adaptive Framework for Developing a Large Language Model-Based Agent for Natural Product Domain Research	提出ChatT2以解决微生物天然产物研究中的复杂性问题	large language model multimodal chain-of-thought
2	EADC: Evaluation of Advanced and Deep-level Compliance in Large Language Models	提出EADC以解决大语言模型合规性评估问题	large language model
3	AgenticSizing: A Large Language Model-based Multi-Agent Framework for Analog Circuit Sizing	提出基于大语言模型的多智能体框架以解决模拟电路优化问题	large language model
4	Deflecting the Value Compass: Interacting with Large Language Models Temporarily Shifts Human Value Priorities Toward Personal Focus	探讨与大型语言模型互动对人类价值观的影响	large language model
5	VideoX-Qwen: Data-Centric Instruction-Based Video Editing	提出VideoX-Qwen以解决指令驱动视频编辑的挑战	multimodal instruction following
6	Toolcompass: Guiding Tool Trialing, Not Suppressing It	提出ToolCompass以指导工具试用，解决试用效率低下问题	large language model
7	Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents	提出Growing Harness以解决LLM代理控制决策重复问题	large language model
8	Metrics Failure in LLM-Based Code Vulnerability Repair: An Empirical Study and a Change-Aware Screen	提出变更感知评估以解决LLM代码漏洞修复中的指标失效问题	large language model
9	Does AI Save Time on Product Design? A Randomized Controlled Experiment of AI Prompt-to-Design Workflows	通过随机对照实验评估AI在产品设计中的时间节省效果	large language model
10	From Alignment to Access Control: A Framework for GenAI Policy Enforcement	提出系统化方法以解决生成AI政策执行的混乱问题	large language model
11	On the security and privacy of LLMs in Mobility	评估大型语言模型在移动领域的安全与隐私挑战	large language model
12	CQ4OE: A benchmark for assessing LLM-assisted ontology generation from competency questions	提出CQ4OE基准以解决LLM辅助本体生成评估问题	large language model
13	CogenPVG: Cognitive-Enhanced Reflective Multi-Agent Framework for Persuasive Video Generation	提出CogenPVG框架以解决说服视频生成问题	multimodal
14	Direct Optimization of Generators for Search in Automated Theorem Proving	提出计算对齐训练以优化自动定理证明中的生成器	large language model
15	Recovering Agentic Sovereignty: Mitigating the Consensus Paradox via Contrastive Epistemic Decoding	提出对比认知解码以缓解共识悖论问题	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	🔗	⭐
16	Dual-Frontier: When Can an Agent Trust Its World Model?	提出Dual-Frontier以解决世界模型信任问题	world model world models
17	Ladders of Thought: A Self-Evolving Curriculum of Progressively Simplified Reasoning Traces	提出Ladders-of-Thought框架以增强小型语言模型的推理能力	distillation large language model
18	SE-MSB: End-to-End Unpaired Speech Enhancement using Mamba Schrödinger Bridges	提出无配对语音增强框架以解决真实环境中的语音恢复问题	Mamba
19	The Limits of Simulated Societies: How Post-Training and Survey Fine-Tuning Erase Cross-Cultural Variance	提出诊断框架以解决模拟社会中的文化差异消失问题	DPO large language model
20	OmniFysics-Nano-V2 Technical Report: Understanding the Physical World Across Modalities	提出OmniFysics-Nano-V2以解决物理世界理解不足问题	reinforcement learning multimodal
21	Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA	提出NB-LoRA以解决后强化学习LLM的推理能力保持问题	reinforcement learning large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
22	LingLan: An Advancing Traditional Chinese Medicine Diagnosis LLM with Multimodal Data	提出LingLan以解决传统中医诊断数据整合问题	PULSE large language model multimodal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
23	A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem	提出A2M框架以优化MCP生态系统中的代理劫持问题	manipulation	✅

⬅️ 返回 cs.AI 首页 · 🏠 返回主页