Experience

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

20 new papers

A weekly snapshot of new work published in Experience.

Period ending 2026-09-14

9 new papers

A weekly snapshot of new work published in Experience.

Period ending 2026-09-07

9 new papers

A weekly snapshot of new work published in Experience.

Inside this field

Focused directions

Focused topic

Experience

Within Experience

100 papersExplore

Focused topic

Skill Evolution

Within Experience

91 papersExplore

Focused topic

Reuse

Within Experience

62 papersExplore

Focused topic

Reusable Skills

Within Experience

58 papersExplore

Focused topic

Reusable Agent Skills

Within Experience

54 papersExplore

Focused topic

Procedural Knowledge

Within Experience

49 papersExplore

Focused topic

Unsupervised Skill Discovery

Within Experience

37 papersExplore

Focused topic

Agent Skill Ecosystems

Within Experience

28 papersExplore

Focused topic

Experience-Driven Learning

Within Experience

25 papersExplore

Focused topic

Skillaudit

Within Experience

15 papersExplore

459 papers

Latest in Experience

Browse all topics →

Behavioral Integrity Verification for AI Agent Skills
May 12, 2026Yuhao Wu, Tung-Ling Li, Hongliang LiuAgent Skill Ecosystems Malicious Code
Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry
May 12, 2026Shoumik Saha, Kazem Faghih, Soheil FeiziReusable Agent Skills Agent Skill Ecosystems
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
May 11, 2026Jinhang Xu, Qiyuan Zhu, Yujun Wu +11Autoresearch Skill Evolution
Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents
May 11, 2026Zhiyuan Fan, Wenwei Jin, Feng Zhang +4Self-Evolving Agents Experience
Towards Understanding Continual Factual Knowledge Acquisition of Language Models: From Theory to Algorithm
May 11, 2026Haoyu Wang, Yifan Shang, Zhongxiang Sun +3Model Pretraining Procedural Knowledge
SkillEvolver: Skill Learning as a Meta-Skill
May 11, 2026Genrui Zhang, Erle Zhu, Jinfeng Zhou +2Skill Evolution Skillaudit
EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents
May 11, 2026Ruofei Ju, Xinrui Wang, Xin Ding +12Skill Evolution Embodied Agents
Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation
May 11, 2026Zhixuan Shen, Jiawei Du, Ziyu Guo +5Embodied Navigation Embodied Agents
Kintsugi: Learning Policies by Repairing Executable Knowledge Bases
May 10, 2026Teng Cao, Yu Deng, Hikaru Shindo +6Embodied Agents Reinforcement-Learning Policies
Skill-R1: Agent Skill Evolution via Reinforcement Learning
May 10, 2026Yash Vishe, Rohan Surana, Xunyi Jiang +8Skill Evolution Agentic Reinforcement-Learning Framework
SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System
May 10, 2026Shuai Pan, Yixiang Liu, Jiaye Gao +7Skill Evolution Multi-Agent Systems
A Prompt-Aware Structuring Framework for Reliable Reuse of AI-Generated Content in the Agentic Web
May 10, 2026Shusaku Egami, Masahiro HamasakiAi-Generated Modular Agentic Framework
Evidence Over Plans: Online Trajectory Verification for Skill Distillation
May 9, 2026Yang Zhou, Zihan Dong, Zhenting Wang +7Unsupervised Skill Discovery Task Synthesis
Methods for Formal Verification of Agent Skills: Three Layers Toward a Mechanically Checkable Capability-Containment Proof
May 9, 2026Alfredo MetereReusable Agent Skills Formal Verification
SkillGen: Verified Inference-Time Agent Skill Synthesis
May 9, 2026Yuchen Ma, Yue Huang, Han Bao +5Reusable Agent Skills Automated Synthesis Techniques
ECHO: Continuous Hierarchical Memory for Vision-Language-Action Models
May 9, 2026Yanbin Hu, Jin Cui, Jiayi Lu +6Vision-Language-Action Models Long-Horizon Planning
Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution
May 9, 2026Feng Xiong, Zengbin Wang, Yong Wang +5Multimodal Agents Reusable Skills
MIND-Skill: Quality-Guaranteed Skill Generation via Multi-Agent Induction and Deduction
May 9, 2026Yixuan Li, Mingshu Cai, Ziyang Xiao +3Reusable Agent Skills
The Echo Amplifies the Knowledge: Somatic Marker Analogues in Language Models via Emotion Vector Re-Injection
May 9, 2026Jared GloverLong-Term Memory Self-Awareness
SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents
May 8, 2026Yongliang Miao, Ziyang Yu, Liang Zhao +2Skill Evolution Large Language Model Agents
How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits
May 8, 2026Michael Li, Nishant SubramaniMechanistic Interpretability Circuits
Tacit Knowledge Extraction via Logic Augmented Generation and Active Inference
May 8, 2026Lorenzo Lamazzi, Aldo Gangemi, Alessio Giberti +4Procedural Knowledge Neuro-Symbolic Framework
SkillSelect-Serve: QoS-Aware Budgeted Skill Service Recommendation for LLM Agents
May 8, 2026Jingyuan Zheng, Dongjing Wang, Xin Zhang +7Reusable Agent Skills Large Language Model Agents
Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models
May 8, 2026Xiaoze Liu, Dhananjay Ram, Yuting Zhang +3Reinforcement Learning Post-Training Group Relative Policy Optimization
Kernel Foundry: A Diagnosis-driven Evolutionary Kernel Optimizer with Multi-Experts
May 8, 2026Zixuan Huang, Da Chen, Kecheng Huang +5Graphics Processing Unit Kernels Code Optimization
Learning Agent Routing From Early Experience
May 8, 2026Yimin Wang, Jiahao Qiu, Xuan Qi +6Large Language Model Routing LLM Inference Efficiency
Rethinking Experience Utilization in Self-Evolving Language Model Agents
May 8, 2026Weixiang Zhao, Yingshuo Wang, Yichen Zhang +6Self-Evolving Agents Experience
Self-Consolidating Language Models: Continual Knowledge Incorporation from Context
May 8, 2026Zekun Wang, Anant Gupta, Zihan Dong +1Efficient Long-Context Inference Consolidation
Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries
May 7, 2026Kun Zeng, Yu Huo, Siyu Zhang +6Agent Skill Ecosystems Agentic Retrieval
SkillOS: Learning Skill Curation for Self-Evolving Agents
May 7, 2026Siru Ouyang, Jun Yan, Yanfei Chen +13Skill Evolution Self-Evolving Agents
Grokers: Bottom-Up Inductive Comprehension and Write-Time Intelligence over Typed Knowledge Graphs
May 7, 2026Gregory MagarshakKnowledge Graphs Procedural Knowledge
Towards Distributed Inference of LLMs on a P2P Network
May 7, 2026Shabari S Nair, Krishanu SainiLLM Inference Efficiency Cache
Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
May 7, 2026Alireza Modirshanechi, Benjamin Eysenbach, Peter Dayan +1Goal-Conditioned Reinforcement Learning Unsupervised Skill Discovery
Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
May 7, 2026Yaorui Shi, Yuxin Chen, Zhengxi Lu +6Skill Evolution Agentic Reinforcement-Learning Framework
From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
May 7, 2026Jinghao Luo, Yuchen Tian, Chuxue Cao +6Agent Memory Experience
Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
May 6, 2026Andreas Pattichis, Constantine DovrolisSynaptic Plasticity Procedural Knowledge
The Pinocchio Dimension: Phenomenality of Experience as the Primary Axis of LLM Psychometric Differences
May 6, 2026Hubert Plisiecki, Sabina Siudaj, Kacper Dudzic +4Psychometrics Experience
Skill Neologisms: Towards Skill-based Continual Learning
May 6, 2026Antonin Berthon, Nicolas Astorga, Mihaela van der SchaarUnsupervised Skill Discovery Efficient Continual Learning
An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration
May 5, 2026Dutao Zhang, Tian LiaoAgentic Retrieval Hievi-Rag
Transformers with Selective Access to Early Representations
May 5, 2026Skye Gunasekaran, Téa Wright, Rui-Jie Zhu +1Transformer Architectures Early Layers
SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
May 5, 2026Yipeng Ouyang, Yi Xiao, Yuhao Gu +1Agent Skill Ecosystems Large Language Model Agents
VLMaxxing through FrameMogging Training-Free Anti-Recomputation for Video Vision-Language Models
May 5, 2026JF Bastien, Sam D'AmicoVideo-Language Models Reuse
cotomi Act: Learning to Automate Work by Watching You
May 4, 2026Masafumi Oyamada, Kunihiro Takeoka, Kosuke Akimoto +5Computer-Use Agents Browser Agent
From Sensors to Insight: Rapid, Edge-to-Core Application Development for Sensor-Driven Applications
May 4, 2026Komal Thareja, Anirban Mandal, Ewa DeelmanSensors Edge Computing
An Empirical Study of Agent Skills for Healthcare: Practice, Gaps, and Governance
May 4, 2026Gelei Xu, Ningzhi Tang, Xueyang Li +4Reusable Agent Skills Healthcare
ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning
May 4, 2026Safayat Bin Hakim, Keyan Guo, Wenkai Tan +3Neuro-Symbolic Framework Large Language Model Agents
Combining Trained Models in Reinforcement Learning
May 4, 2026Ujjwal Patil, Javad GhofraniDeep Reinforcement Learning Cross-Task Knowledge Transfer
KG-First, LLM-Fallback: A Hybrid Microservice for Grounded Skill Search and Explanation
May 2, 2026Ngoc Luyen Le, Marie-Hélène Abel, Bertrand LaforgeUnsupervised Skill Discovery Knowledge Graphs
AI Expert Twin: Capturing Expert Cognition for Human-Centred, Practice-Based Learning
May 2, 2026Annie Yuan, Xiaohua Chen, Kalina Yacef +1Tutors Experience-Driven Learning
Interpretable experiential learning based on state history and global feedback
May 1, 2026Anton KoloninExperience-Driven Learning Feedback Learning
Synthetic Computers at Scale for Long-Horizon Productivity Simulation
Apr 30, 2026Tao Ge, Baolin Peng, Hao Cheng +1Computer-Use Agents Task Synthesis
Measuring research data reuse in scholarly publications using generative artificial intelligence: Open Science Indicator development and preliminary results
Apr 30, 2026Lauren Cadwallader, Iain Hrynaszkiewicz, parth sarin +1Real Datacite Dois Academic Papers
From Context to Skills: Can Language Models Learn from Context Skillfully?
Apr 30, 2026Shuzheng Si, Haozhe Zhao, Yu Lei +10In-Context Learning Reusable Agent Skills
Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO
Apr 30, 2026Yu Tian, Jiawei Chen, Lifan Zheng +5Skill Evolution Group Relative Policy Optimization
When Hidden States Drift: Can KV Caches Rescue Long-Range Speculative Decoding?
Apr 29, 2026Tianyu Liu, Yuhao Shen, Xinyi Hu +8Speculative Decoding Kv-Cache Blocks
DreamProver: Evolving Transferable Lemma Libraries via a Wake-Sleep Theorem-Proving Agent
Apr 29, 2026Youyuan Zhang, Jialiang Sun, Hangrui Bi +4Theorem Procedural Knowledge
When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agents
Apr 29, 2026Qisheng Hu, Quanyu Long, Wenya WangContinual Learning Methods Large Language Model Agents
TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning
Apr 28, 2026Dominik Żurek, Kamil Faber, Marcin Pietron +2Offline Reinforcement Learning Efficient Continual Learning
Toward Scalable Terminal Task Synthesis via Skill Graphs
Apr 28, 2026Zhiyuan Fan, Tinghao Yu, Yuanjun Cai +8Task Synthesis Skill Evolution
Skill Retrieval Augmentation for Agentic AI
Apr 27, 2026Weihang Su, Jianming Long, Qingyao Ai +6Reusable Skills Text Corpora

May 12, 2026 · cs.CRJ/K move · Enter open · S save

Behavioral Integrity Verification for AI Agent Skills

Yuhao Wu, Tung-Ling Li, Hongliang Liu

Palo Alto Networks

Agent skills extend LLM agents with privileged third-party capabilities such as filesystem access, credentials, network calls, and shell execution. Existing safety work catches malicious prompts and risky runtime actions, but the skill artifact itself goes unverified. We formalize this as the behavioral integrity verification (BIV) problem: a typed set comparison between declared and actual capabilities over a shared taxonomy that bridges code, instructions, and metadata. The BIV framework instantiates this comparison by pairing deterministic code analysis with LLM-assisted capability extraction. The resulting structured evidence supports three downstream analyses: deviation taxonomy, root-cause classification, and malicious-skill detection. On 49,943 skills from the OpenClaw registry, the deviation taxonomy reveals a pervasive description-implementation gap: 80.0% of skills deviate from declared behavior, with four novel compound-threat categories surfaced. Root-cause classification finds that deviations are mostly oversight, not malice: 81.1% trace to developer oversight and 18.9% to adversarial intent, with 5.0% of skills carrying predicted multi-stage attack chains. On a 906-skill malicious-skill detection benchmark, BIV reaches an F1 of 0.946, outperforming state-of-the-art rule-based and single-pass LLM baselines. These results demonstrate behavioral integrity auditing for agent skills at scale.

Agent Skill Ecosystems Malicious Code Algorithm Auditing Transferable Attack

Open paper Ask about it PDF