HEXIS: Compiling Agent Skills into Extended Finite State Machines

arXiv:2609.30123 · cs.AI · Submitted 2026-09-24 · Read on arXiv

cs.AI

Submitted: 2026-09-24

Updated: 2026-09-26

Code: https://github.com/anomalyco/opencode

Terminology

• Trace — 34× in this paper · explained in 2 episodes
• Benchmark — 28× in this paper · explained in 2 episodes
• Agent Skills — 11× in this paper · explained in 1 episode
• Alignment — 8× in this paper · explained in 1 episode
• Verification — 4× in this paper · explained in 2 episodes
• Abstention — 3× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Agent Skills Matter: Inferring Proprietary Skills from Execution Trajectories
• LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches
• SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
• SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints
• StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
• TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows
• SkillOpt: Executive Strategy for Self-Evolving Agent Skills
• Compile, Then Page: Executable SOP Programs and a Capability-Gated Runtime for Procedural LLM Agents
• Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection