# Quasar: A Programming Language Specialized for LLM Code Actions

arXiv: https://arxiv.org/abs/2506.12202 · HTML: https://mlsanity.com/paper/2506.12202/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 13 Jun 2025.

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

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [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)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [Defeating Prompt Injections by Design](https://mlsanity.com/paper/2503.18813/) (2025)
- [Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Control](https://mlsanity.com/paper/2110.01052/) (2021)
- [Conformal Language Modeling](https://mlsanity.com/paper/2306.10193/) (2023)
- [The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies](https://mlsanity.com/paper/2407.19354/) (2024)
- [Uncertainty Estimation and Quantification for LLMs: A Simple Supervised Approach](https://mlsanity.com/paper/2404.15993/) (2024)
- [From LLM to Conversational Agent: A Memory Enhanced Architecture with Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2401.02777/) (2024)
- [Torch.fx: Practical Program Capture and Transformation for Deep Learning in Python](https://mlsanity.com/paper/2112.08429/) (2021)
- [Measuring The Impact Of Programming Language Distribution](https://mlsanity.com/paper/2302.01973/) (2023)
- [TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction](https://mlsanity.com/paper/2307.04642/) (2023)
- [Conformal Structured Prediction](https://mlsanity.com/paper/2410.06296/) (2024)
- [Opportunistically Parallel Lambda Calculus](https://mlsanity.com/paper/2405.11361/) (2024)
- [Uncertainty Quantification for Neurosymbolic Programs via Compositional Conformal Prediction](https://mlsanity.com/paper/2405.15912/) (2024)
- [REDO: Execution-Free Runtime Error Detection for COding Agents](https://mlsanity.com/paper/2410.09117/) (2024)

## Built on by (most cited first, 4 of 4)

- [Enforcing Temporal Constraints for LLM Agents](https://mlsanity.com/paper/2512.23738/) (2025)
- [The LLMbda Calculus: AI Agents, Conversations, and Information Flow](https://mlsanity.com/paper/2602.20064/) (2026)
- [Sharing State Between Prompts and Programs](https://mlsanity.com/paper/2512.14805/) (2025)
- [Beyond Human-Readable: Rethinking Software Engineering Conventions for the Agentic Development Era](https://mlsanity.com/paper/2604.07502/) (2026)

## Abstract (arXiv)

Large language models (LLMs) often call external tools to solve tasks. One effective strategy is for LLMs to write code, enabling them to use complex control flow such as conditionals and loops. Such code actions are typically represented as Python code, since LLMs are proficient at writing it. However, many programming language features that would support more effective code actions are difficult to implement for Python. We propose separating internal code that captures program logic from external calls to tools that interact with the world. New features can then easily be implemented by (1) annotating external calls with the effects relevant to that feature, and (2) modifying the execution of the internal code to track this information. We develop a novel programming language, Quasar, that implements this idea. To illustrate its utility, we implement several useful features on top of Quasar to enhance code actions: access control with batched user queries to improve security, autoparallelization of external calls to reduce latency, and conformal prediction for uncertainty quantification to mitigate hallucinations.