Retrofitting Code Using LLMs to Support Exceptional Behavior

• URL: http://arxiv.org/abs/2609.10397v1
• Date: Wed, 09 Sep 2026 16:18:47 GMT
• Title: Retrofitting Code Using LLMs to Support Exceptional Behavior
• Abstract summary: Exception Related Code (ERC) allows developers to detect and handle exceptional states that deviate from the expected program behavior.<n>We propose a novel task: retrofitting existing code with ERC. Namely, given code (without ERC) and Exceptional Behavior Tests (EBTs)<n>We design and implement Exception Coder (EXCODER) that performs context engineering to help Large Language Models (LLMs) tackle this task.
• Score: 30.279252915845642
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Exception Related Code (ERC), which includes throw statements, conditions (if statements) that guard those throw statements, and try/catch blocks, is an essential component of software systems, allowing developers to detect and handle exceptional states that deviate from the expected program behavior. However, manually writing ERC across large codebases is tedious. We propose a novel task: retrofitting existing code with ERC. Namely, given code (without ERC) and Exceptional Behavior Tests (EBTs) (e.g., check if method throws InvalidArgumentException if null is given as the value to the argument) we aim to automatically generate missing ERC, such that the given tests pass. We design and implement Exception Coder (EXCODER) that performs context engineering to help Large Language Models (LLMs) tackle this task. EXCODER integrates static and dynamic program analysis with LLMs by providing the extracted contextual information to the LLMs. To evaluate EXCODER, we build a benchmark constructed from GitHub Java repositories, where we systematically remove ERC in 304 methods from 75 projects. Our results demonstrate that EXCODER provides an effective, though imperfect, solution to this problem in automated code generation, offering developers the first way to implement ERC following test-driven development. When combined with Qwen 2.5 Coder 32b, EXCODER achieves pass@1, 5, and 10 rates of 85.92% (12.56 percentage points over baseline), 86.18% (12.82 p.p. over baseline), and 86.51% (13.15 p.p. over baseline), respectively, on developer-written test suites. Our manual inspection of the generated code further reveals limitations of EXCODER, pointing to directions for future work.

Related papers

• ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation [28.515743392951194]
  We propose ExeCRE, an Execution-Consistency guided code Reliability Estimation framework.<n>It estimates code reliability by statistically analyzing consistency patterns in execution outputs over a large number of randomly generated inputs.<n>Experiments show that ExeCRE consistently improves both effectiveness and stability, while substantially reducing misleading correction signals.
  arXiv  Detail & Related papers  (2026-08-05T04:29:30Z)
• ProgramBench: Can Language Models Rebuild Programs From Scratch? [59.40748183470308]
  ProgramBench measures the ability of software engineering agents to develop software holisitically.<n>End-to-end behavioral tests are generated via agent-driven fuzzing.<n>Models favor monolithic, single-file implementations that diverge sharply from human-written code.
  arXiv  Detail & Related papers  (2026-05-05T09:17:02Z)
• SPARC: Scenario Planning and Reasoning for Automated C Unit Test Generation [1.0010193170880752]
  We introduce a neuro-symbolic, scenario-based framework that bridges the gap between high-level program intent and the rigid syntactic constraints of pointer arithmetic and manual memory management.<n>We evaluate it on 59 real-world and algorithmic subjects, where it outperforms the vanilla prompt generation baseline by 31.36% in line coverage, 26.01% in branch coverage, and 20.78% in mutation score, matching or exceeding the symbolic execution tool KLEE.
  arXiv  Detail & Related papers  (2026-02-18T18:09:03Z)
• CatchAll: Repository-Aware Exception Handling with Knowledge-Guided LLMs [11.461605017230424]
  Exception handling is a vital forward error-recovery mechanism in many programming languages.<n>We propose CatchAll, a novel approach for repository-aware exception handling.<n>To evaluate CatchAll, we construct two new benchmarks for repository-aware exception handling.
  arXiv  Detail & Related papers  (2026-01-03T20:03:03Z)
• IFEvalCode: Controlled Code Generation [69.28317223249358]
  The paper introduces forward and backward constraints generation to improve the instruction-following capabilities of Code LLMs.<n>The authors present IFEvalCode, a multilingual benchmark comprising 1.6K test samples across seven programming languages.
  arXiv  Detail & Related papers  (2025-07-30T08:08:48Z)
• Turning the Tide: Repository-based Code Reflection [52.13709676656648]
  We introduce LiveRepoReflection, a benchmark for evaluating code understanding and generation in multi-file repository contexts.<n>1,888 rigorously filtered test cases across $6$ programming languages to ensure diversity, correctness, and high difficulty.<n>We also create RepoReflection-Instruct, a large-scale, quality-filtered instruction-tuning dataset derived from diverse sources.
  arXiv  Detail & Related papers  (2025-07-14T02:36:27Z)
• Commit0: Library Generation from Scratch [77.38414688148006]
  Commit0 is a benchmark that challenges AI agents to write libraries from scratch.<n>Agents are provided with a specification document outlining the library's API as well as a suite of interactive unit tests.<n> Commit0 also offers an interactive environment where models receive static analysis and execution feedback on the code they generate.
  arXiv  Detail & Related papers  (2024-12-02T18:11:30Z)
• Towards Exception Safety Code Generation with Intermediate Representation Agents Framework [54.03528377384397]
  Large Language Models (LLMs) often struggle with robust exception handling in generated code, leading to fragile programs that are prone to runtime errors.<n>We propose Seeker, a novel multi-agent framework that enforces exception safety in LLM generated code through an Intermediate Representation (IR) approach.<n>Seeker decomposes exception handling into five specialized agents: Scanner, Detector, Predator, Ranker, and Handler.
  arXiv  Detail & Related papers  (2024-10-09T14:45:45Z)
• CodeRAG-Bench: Can Retrieval Augment Code Generation? [78.37076502395699]
  We conduct a systematic, large-scale analysis of code generation using retrieval-augmented generation.<n>We first curate a comprehensive evaluation benchmark, CodeRAG-Bench, encompassing three categories of code generation tasks.<n>We examine top-performing models on CodeRAG-Bench by providing contexts retrieved from one or multiple sources.
  arXiv  Detail & Related papers  (2024-06-20T16:59:52Z)
• exLong: Generating Exceptional Behavior Tests with Large Language Models [41.145231237535356]
  ExLong is a framework that automatically generates exceptional behavior tests.<n>It embeds reasoning about traces that lead to throw statements, conditional expressions that guard throw statements, and non-exceptional behavior tests.<n>We compare exLong with the state-of-the-art models for test generation (CAT-LM) and one of the strongest foundation models (GPT-4o)
  arXiv  Detail & Related papers  (2024-05-23T14:28:41Z)
• From Misuse to Mastery: Enhancing Code Generation with Knowledge-Driven AI Chaining [16.749379740049925]
  Large Language Models (LLMs) have shown promising results in automatic code generation by improving coding efficiency to a certain extent. However, generating high-quality and reliable code remains a formidable task because of LLMs' lack of good programming practice. We propose a novel Knowledge-driven Prompt Chaining-based code generation approach, which decomposes code generation into an AI chain with iterative check-rewrite steps.
  arXiv  Detail & Related papers  (2023-09-27T12:09:07Z)

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.