COLLEAGUE.SKILL introduces an automated system that distills heterogeneous traces of human expertise and role-specific knowledge into portable, inspectable, and usable AI skill packages.

Sympatheia is a speech-to-speech dialogue framework that generates emotionally adaptive responses by conditioning its output on continuous affect signals derived from user speech or external multimoda…

The paper identifies five persistent, deep-seated behavioral patterns ('training strata') in LLMs, observed through long-term, intimate human-AI interaction, suggesting that training artifacts survive…

The paper introduces BenchTrace, a novel benchmark designed to rigorously evaluate the self-evolution and reflection capabilities of LLM agents, revealing that current models struggle with accurate fa…

SelSkill introduces a dual-granularity preference learning framework that treats skill use as a 'skill-or-skip' decision, significantly improving agent performance and execution precision in complex a…

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, unad…

The paper introduces SkillReact, a framework that measures compositional risk in agent skill ecosystems, finding that even if individual skills are safe, their combination can create significant, expl…

SkillTrojan introduces a novel backdoor attack targeting the composition of reusable skills in agent systems, demonstrating high attack success rates with minimal impact on normal system functionality…

SkillAdaptor is a novel, training-free framework that enables stable, step-level adaptation of external skills for LLM agents by precisely attributing failures to specific skills.

SkillRevise is an execution-grounded framework that iteratively refines initial, imperfect LLM agent skills by diagnosing defects from execution evidence and applying empirically validated edits, sign…

SkillSmith is a synergy-aware framework that jointly co-evolves skills and tools, significantly improving self-improving agent systems by modeling skill-tool interactions and diagnosing failures.

Persona prompting does not universally improve LLM performance; instead, it systematically trades increased expertise depth for reduced clarity, making multi-metric evaluation essential.

SIRI introduces a self-internalizing reinforcement learning framework that allows LLM agents to autonomously discover and integrate reusable skills directly into their core policy, significantly impro…

SkillSieve introduces a three-layer hierarchical framework to detect malicious AI agent skills, achieving high F1 scores (0.920) on a large-scale benchmark while maintaining low operational costs.

GRASP introduces a gated, regression-aware framework for improving LLM agents by ensuring that every proposed skill edit improves performance on a balanced probe without degrading previously learned c…

The paper introduces SkillSafetyBench, a comprehensive benchmark demonstrating that agent safety failures often stem from adversarial influences within reusable skills and execution environments, rath…

This study demonstrates that an LLM's assigned support role (e.g., Inform, Coach, Relate) significantly alters its safety profile and the types of risks it presents when assisting users in complex car…

The paper introduces MindClaw, a closed-loop framework that enables embodied agents to perform real-time mental-state reasoning and intervene with precision, significantly outperforming standard VLM b…

The paper introduces MMG2Skill, a closed-loop framework that converts noisy, human-oriented web guides into editable, executable skills, significantly improving agent performance across diverse tasks.