会员服务
ECOS: Environment-Calibrated On-Policy Self-Distillation for Language Agents
Arxiv
0+阅读 · 11月9日
SkillCODER: Towards Auditing and Attribution of Copyright Infringement in LLM Agent Skills
Arxiv
0+阅读 · 11月8日
SkillDuet: Co-Evolving Models and Skills through Response Feedback
Arxiv
0+阅读 · 11月9日
StealthyPoison: Manipulating LLM Agent Behavior through Procedural Poisoning of Third-Party Skills
Arxiv
0+阅读 · 11月9日
MIRIX-2.0: Multi-Agent Memory System
Arxiv
0+阅读 · 11月9日
HandMimicX: Learning Human-Like Dexterous Manipulation via an Object-Centric Policy from Egocentric Videos
Arxiv
0+阅读 · 11月9日
Do Time-Series Foundation Models Forecast Index-Futures Returns? A Preregistered Evaluation of Models, Metrics, and Input Representations
Arxiv
0+阅读 · 11月9日
SMO: Compiling Natural Language Skills into Graphs of Reusable State-Move-Outcome Bricks
Arxiv
0+阅读 · 11月9日
EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation
Arxiv
0+阅读 · 11月9日
SkillAny: Online Skill Learning for Language Agents at Any Intermediate State
Arxiv
0+阅读 · 11月7日
Separation of Skilling Context for Standard Operating Procedure-based Agents
Arxiv
0+阅读 · 11月8日
Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation
Arxiv
0+阅读 · 11月8日
Vibe-FDTR: An agent-oriented framework for reproducible frequency-domain thermoreflectance data analysis
Arxiv
0+阅读 · 11月7日
When Experience Becomes a Backdoor: Poisoning Self-Evolving LLM Agents via Failure-Aware Task Optimization
Arxiv
0+阅读 · 11月7日
The Devil Wears Markdown: Detecting Malicious Intent Hidden in AI Agent Skill Instructions through Hybrid Static, Dynamic, and Agentic Analysis
Arxiv
0+阅读 · 11月7日
参考链接
微信扫码咨询专知VIP会员
Top