arXiv AI
5d ago
Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents
arXiv:2608. 12851v1 Announce Type: new Abstract: Self-improving LLM agents convert successful trajectories into persistent cross-task state.
OBLIVION: Workflow-Level Operational Skill Unlearning for Deployed Agents
arXiv:2608. 08264v1 Announce Type: new Abstract: Large language model agents are becoming operational interfaces to files, memories, registries, and external tools.
Related stories
arXiv AI
Jun 17
SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents
arXiv:2602. 14211v3 Announce Type: replace-cross Abstract: Agent skills extend LLM agents with task-specific instructions, executable scripts, and auxiliary resources, improving reusability but creating a new supply-chain attack surface.
arXiv AI
22h ago
TRUSS: Towards Task-Reliable and User-Safe Automated Agent Skill Generation
arXiv:2608. 17588v1 Announce Type: new Abstract: Agent Skills package reusable natural language procedures with executable resources, enabling software agents to acquire task specific capabilities without model adaptation.
Hugging Face Trending Papers
1d ago
TRUSS: Towards Task-Reliable and User-Safe Automated Agent Skill Generation
Agent Skills package reusable natural language procedures with executable resources, enabling software agents to acquire task specific capabilities without model adaptation. Automatically generating such Skills can improve task performance, yet evaluating a candidate solely from its artifact or final task outcome leaves unresolved which actions the equipped agent will perform and which side effects those actions will produce.
arXiv AI
Jul 21
AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows
arXiv:2607. 16345v1 Announce Type: cross Abstract: Modern agentic systems increasingly rely on skills: installable packages of natural language and code that teach an LLM agent to perform a domain task.
arXiv AI
Aug 12
From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents
arXiv:2608. 10502v1 Announce Type: new Abstract: Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed record can alter reasoning, tool use, answers, and subsequent memory writes.
arXiv AI
Aug 6
Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent Skills
arXiv:2608. 04192v1 Announce Type: cross Abstract: Closed source agent skills may encode proprietary instructions, scripts, constants, and data.
arXiv AI
22h ago
SkillEffect: Checked Lowering for Memory-Bounded Agent Tools
arXiv:2608. 17007v1 Announce Type: new Abstract: Agent Skills can specify procedural and resource obligations for tool use, and language models instantiate them as concrete programs.
arXiv AI
Jun 9
SKILL.nb: Selective Formalization and Gated Execution for Durable Agent Workflows
arXiv:2606. 08049v1 Announce Type: new Abstract: AI agents increasingly turn past experience into reusable artifacts such as code, workflows, and procedural memories.
arXiv AI
Jul 31
MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
arXiv:2607. 27080v1 Announce Type: cross Abstract: Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist.
arXiv AI
Jun 2
Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents
arXiv:2606. 01567v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on reusable skills i.
arXiv AI
Jul 24
Workflow-Localized Mechanism Learning: Attribution-Guided Repair and Knowledge Reuse for Structured Agent Skills
arXiv:2607. 20999v1 Announce Type: new Abstract: Agent Skills package reusable procedural knowledge as external artifacts for frozen language-model agents, yet existing optimizers do not jointly resolve where a failure occurs in a workflow, which mechanism caused it, and how relevant knowledge from third-party Skills should be reused locally.