# Tapas Are Free! Training-Free Adaptation of Programmatic Agents via LLM-Guided Program Synthesis in Dynamic Environments

arXiv: https://arxiv.org/abs/2508.11425 · HTML: https://mlsanity.com/paper/2508.11425/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 49 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 16 of 16)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [Retrieval Augmented Code Generation and Summarization](https://mlsanity.com/paper/2108.11601/) (2021)
- [Large Language Models Meet NL2Code: A Survey](https://mlsanity.com/paper/2212.09420/) (2022)
- [RedCode: Risky Code Execution and Generation Benchmark for Code Agents](https://mlsanity.com/paper/2411.07781/) (2024)
- [SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning](https://mlsanity.com/paper/1811.00090/) (2018)
- [PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making](https://mlsanity.com/paper/1804.07779/) (2018)
- [LLM-Powered AI Agent Systems and Their Applications in Industry](https://mlsanity.com/paper/2505.16120/) (2025)
- [Large Language Models are Autonomous Cyber Defenders](https://mlsanity.com/paper/2505.04843/) (2025)
- [Learning STRIPS Action Models with Classical Planning](https://mlsanity.com/paper/1903.01153/) (2019)
- [BlendRL: A Framework for Merging Symbolic and Neural Policy Learning](https://mlsanity.com/paper/2410.11689/) (2024)
- [Enhancing Robustness of LLM-Driven Multi-Agent Systems through Randomized Smoothing](https://mlsanity.com/paper/2507.04105/) (2025)
- [ANSR-DT: A Neuro-Symbolic Framework for Adaptive and Explainable Digital Twins](https://mlsanity.com/paper/2501.08561/) (2025)

## Built on by (most cited first, 9 of 9)

- [Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage](https://mlsanity.com/paper/2601.01685/) (2026)
- [Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment](https://mlsanity.com/paper/2510.14008/) (2025)
- [TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization](https://mlsanity.com/paper/2601.22776/) (2026)
- [TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems](https://mlsanity.com/paper/2601.10120/) (2026)
- [FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness](https://mlsanity.com/paper/2605.08896/) (2026)
- [Responsible Agentic AI Requires Explicit Provenance](https://mlsanity.com/paper/2605.17169/) (2026)
- [Dive into Ambiguity: A*-Inspired Multi-Agents Commonsense Obfuscation Attack on LLM Prompts](https://mlsanity.com/paper/2606.01441/) (2026)
- [SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces](https://mlsanity.com/paper/2607.02345/) (2026)
- [Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models](https://mlsanity.com/paper/2605.01605/) (2026)

## Abstract (arXiv)

Autonomous agents in safety-critical applications must continuously adapt to dynamic conditions without compromising performance and reliability. This work introduces TAPA (Training-free Adaptation of Programmatic Agents), a novel framework that positions large language models (LLMs) as intelligent moderators of the symbolic action space. Unlike prior programmatic agents typically generate a monolithic policy program or rely on fixed symbolic action sets, TAPA synthesizes and adapts modular programs for individual high-level actions, referred to as logical primitives. By decoupling strategic intent from execution, TAPA enables meta-agents to operate over an abstract, interpretable action space while the LLM dynamically generates, composes, and refines symbolic programs tailored to each primitive. Extensive experiments across cybersecurity and swarm intelligence domains validate TAPA's effectiveness. In autonomous DDoS defense scenarios, TAPA achieves 77.7% network uptime while maintaining near-perfect detection accuracy in unknown dynamic environments. In swarm intelligence formation control under environmental and adversarial disturbances, TAPA consistently preserves consensus at runtime where baseline methods fail. This work promotes a paradigm shift for autonomous system design in evolving environments, from policy adaptation to dynamic action adaptation.