# Agents as Software: A Programming Languages Agenda for Agent Reliability

arXiv: https://arxiv.org/abs/2609.32198 · HTML: https://mlsanity.com/paper/2609.32198/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 53 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Neural Probabilistic Logic Programming in DeepProbLog](https://mlsanity.com/paper/1907.08194/) (2019)
- [PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts](https://mlsanity.com/paper/2306.04528/) (2023)
- [AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents](https://mlsanity.com/paper/2503.18666/) (2025)
- [Sociotechnical Safety Evaluation of Generative AI Systems](https://mlsanity.com/paper/2310.11986/) (2023)
- [Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction](https://mlsanity.com/paper/2210.05791/) (2022)
- [Prompting Is Programming: A Query Language for Large Language Models](https://mlsanity.com/paper/2212.06094/) (2022)
- [Scallop: A Language for Neurosymbolic Programming](https://mlsanity.com/paper/2304.04812/) (2023)
- [Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning"](https://mlsanity.com/paper/2006.11524/) (2020)
- [Enforcing Temporal Constraints for LLM Agents](https://mlsanity.com/paper/2512.23738/) (2025)
- [AgentGuard: Runtime Verification of AI Agents](https://mlsanity.com/paper/2509.23864/) (2025)
- [PDL: A Declarative Prompt Programming Language](https://mlsanity.com/paper/2410.19135/) (2024)
- [PromptPex: Automatic Test Generation for Language Model Prompts](https://mlsanity.com/paper/2503.05070/) (2025)
- [Agentproof: Static Verification of Agent Workflow Graphs](https://mlsanity.com/paper/2603.20356/) (2026)
- [Data Extraction via Semantic Regular Expression Synthesis](https://mlsanity.com/paper/2305.10401/) (2023)
- [APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts](https://mlsanity.com/paper/2406.13161/) (2024)
- [Willful Disobedience: Automatically Detecting Failures in Agentic Traces](https://mlsanity.com/paper/2603.23806/) (2026)
- [Open Agent Specification (Agent Spec): A Unified Representation for AI Agents](https://mlsanity.com/paper/2510.04173/) (2025)
- [Composing Neural Learning and Symbolic Reasoning with an Application to Visual Discrimination](https://mlsanity.com/paper/1907.05878/) (2019)
- [A Closer Look at the Existing Risks of Generative AI: Mapping the Who, What, and How of Real-World Incidents](https://mlsanity.com/paper/2505.22073/) (2025)
- [An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts](https://mlsanity.com/paper/2501.12521/) (2025)

## Abstract (arXiv)

AI agents increasingly resemble software systems: they call tools, remember facts, follow policies, delegate work, and take actions with real consequences. % Yet the ``program'' of an agent is scattered across prompts, tools, memories, workflows, and execution traces, making its behavior difficult to inspect through ordinary testing and debugging alone. % This essay argues that a programming-systems perspective offers a natural lens for making agents reliable. % We recast agents as programmable artifacts whose behavior can be specified over traces and state, checked before deployment, monitored during execution, and improved from observed failures. % The goal is not to make probabilistic agents behave like deterministic programs, but to give them enough structure that their behavior can be reasoned about, controlled, and repaired.