Agents as Software: A Programming Languages Agenda for Agent Reliability

arXiv:2609.32198 · cs.PL, cs.AI · Submitted 2026-09-26 · Read on arXiv

cs.PL, cs.AI

Submitted: 2026-09-26

Updated: 2026-09-26

Terminology

• Trace — 48× in this paper · explained in 2 episodes
• Abstraction — 18× in this paper · explained in 1 episode
• Provenance — 13× in this paper · explained in 4 episodes
• Verification — 11× in this paper · explained in 2 episodes
• AI Agents — 8× in this paper · explained in 2 episodes
• Agentic System — 3× in this paper · explained in 2 episodes
• Generative AI — 3× in this paper · explained in 2 episodes
• Admissibility — 2× in this paper · explained in 2 episodes
• Agentic Framework — 2× in this paper · explained in 6 episodes
• Analyzer — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Formal Methods — 2× in this paper · explained in 3 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Axioms — 1× in this paper · explained in 2 episodes
• Formal Verification — 1× in this paper · explained in 2 episodes
• Ontology — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Open Agent Specification (Agent Spec): A Unified Representation for AI Agents
• AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
• APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts
• The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators
• Enforcing Temporal Constraints for LLM Agents
• Tracking Capabilities for Safer Agents
• An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts
• Toolformer: Language Models Can Teach Themselves to Use Tools
• PromptPex: Automatic Test Generation for Language Model Prompts
• PDL: A Declarative Prompt Programming Language
• AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
• Sociotechnical Safety Evaluation of Generative AI Systems
• ReAct: Synergizing Reasoning and Acting in Language Models
• SGLang: Efficient Execution of Structured Language Model Programs

Related papers

• Griotte: Verified Compartmentalisation via Capabilities
• GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2
• Quasar: A Programming Language Specialized for LLM Code Actions