A Fast, Reliable, and Secure Programming Language for LLM Agents with Code Actions

• URL: http://arxiv.org/abs/2506.12202v1
• Date: Fri, 13 Jun 2025 20:11:22 GMT
• Title: A Fast, Reliable, and Secure Programming Language for LLM Agents with Code Actions
• Authors: Stephen Mell, Botong Zhang, David Mell, Shuo Li, Ramya Ramalingam, Nathan Yu, Steve Zdancewic, Osbert Bastani,
• Abstract summary: We propose a programming language for code actions called Quasar.<n>LLMs can write code in a subset of Python, which is automatically transpiled to Quasar.<n>LLMs with Quasar actions retain strong performance, while reducing execution time when possible by 42%.
• Score: 28.01600045250939
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern large language models (LLMs) are often deployed as agents, calling external tools adaptively to solve tasks. Rather than directly calling tools, it can be more effective for LLMs to write code to perform the tool calls, enabling them to automatically generate complex control flow such as conditionals and loops. Such code actions are typically provided as Python code, since LLMs are quite proficient at it; however, Python may not be the ideal language due to limited built-in support for performance, security, and reliability. We propose a novel programming language for code actions, called Quasar, which has several benefits: (1) automated parallelization to improve performance, (2) uncertainty quantification to improve reliability and mitigate hallucinations, and (3) security features enabling the user to validate actions. LLMs can write code in a subset of Python, which is automatically transpiled to Quasar. We evaluate our approach on the ViperGPT visual question answering agent, applied to the GQA dataset, demonstrating that LLMs with Quasar actions instead of Python actions retain strong performance, while reducing execution time when possible by 42%, improving security by reducing user approval interactions when possible by 52%, and improving reliability by applying conformal prediction to achieve a desired target coverage level.

Related papers

• On the Effectiveness of LLM-as-a-judge for Code Generation and Summarization [54.965787768076254]
  Large Language Models have been recently exploited as judges for complex natural language processing tasks, such as Q&A.<n>We study the effectiveness of LLMs-as-a-judge for two code-related tasks, namely code generation and code summarization.
  arXiv  Detail & Related papers  (2025-07-22T13:40:26Z)
• Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
  Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
  arXiv  Detail & Related papers  (2025-05-28T17:57:47Z)
• EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code [37.712780804235045]
  EffiBench-X is the first multi-language benchmark designed to measure the efficiency of LLM-generated code.<n>It supports Python, C++, Java, JavaScript, Ruby, and Golang.<n>It comprises competitive programming tasks with human-expert solutions as efficiency baselines.
  arXiv  Detail & Related papers  (2025-05-19T11:43:37Z)
• Program Semantic Inequivalence Game with Large Language Models [10.358176296850639]
  Large Language Models (LLMs) can achieve strong performance on everyday coding tasks, but they can fail on complex tasks that require non-trivial reasoning about program semantics.<n>In this work, we explore a method to synthetically generate code reasoning training data based on a semantic inequivalence game SInQ.<n>We prove that this setup enables theoretically unlimited improvement through self-play in the limit of infinite computational resources.
  arXiv  Detail & Related papers  (2025-05-02T20:03:35Z)
• Effective LLM-Driven Code Generation with Pythoness [0.0]
  Pythoness is an embedded domain-specific language for code generation using large language models (LLMs)<n>In Pythoness, developers operate at the level of behavioral specifications when writing functions, classes, or an entire program.<n>We show that Pythoness can successfully leverage a combination of tests and code generation to yield higher quality code than specifications alone.
  arXiv  Detail & Related papers  (2025-01-03T23:14:46Z)
• PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion [96.47420221442397]
  We construct adversarial user instructions by attacking user instructions at sentence, semantic, and multi-language levels. We test 3 closed-source and 4 open-source LLMs using a benchmark that incorporates robustness settings. We find that GPT-4 exhibits the highest performance and strong robustness in our benchmark.
  arXiv  Detail & Related papers  (2024-03-06T15:33:32Z)
• Executable Code Actions Elicit Better LLM Agents [76.95566120678787]
  This work proposes to use Python code to consolidate Large Language Model (LLM) agents' actions into a unified action space (CodeAct) integrated with a Python interpreter, CodeAct can execute code actions and dynamically revise prior actions or emit new actions upon new observations through multi-turn interactions. The encouraging performance of CodeAct motivates us to build an open-source LLM agent that interacts with environments by executing interpretable code and collaborates with users using natural language.
  arXiv  Detail & Related papers  (2024-02-01T21:38:58Z)
• If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents [81.60906807941188]
  Large language models (LLMs) are trained on a combination of natural language and formal language (code) Code translates high-level goals into executable steps, featuring standard syntax, logical consistency, abstraction, and modularity.
  arXiv  Detail & Related papers  (2024-01-01T16:51:20Z)
• ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code [76.84199699772903]
  ML-Bench is a benchmark rooted in real-world programming applications that leverage existing code repositories to perform tasks. To evaluate both Large Language Models (LLMs) and AI agents, two setups are employed: ML-LLM-Bench for assessing LLMs' text-to-code conversion within a predefined deployment environment, and ML-Agent-Bench for testing autonomous agents in an end-to-end task execution within a Linux sandbox environment.
  arXiv  Detail & Related papers  (2023-11-16T12:03:21Z)
• AskIt: Unified Programming Interface for Programming with Large Language Models [0.0]
  Large Language Models (LLMs) exhibit a unique phenomenon known as emergent abilities, demonstrating adeptness across numerous tasks. This paper introduces AskIt, a domain-specific language specifically designed for LLMs. Across 50 tasks, AskIt generated concise prompts, achieving a 16.14 % reduction in prompt length compared to benchmarks.
  arXiv  Detail & Related papers  (2023-08-29T21:44:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.