Pith. sign in

REVIEW 7 cited by

CigaR: Cost-efficient Program Repair with LLMs

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.06598 v2 pith:K6JK5OS6 submitted 2024-02-09 cs.SE cs.LG

Dávid Hidvégi , Khashayar Etemadi , Sofia Bobadilla , Martin Monperrus This is my paper · ORCID
classification cs.SEcs.LG
keywords cigartokensrepaircostllmsnumberprogramuses
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large language models (LLM) have proven to be effective at automated program repair (APR). However, using LLMs can be costly, with companies invoicing users by the number of tokens. In this paper, we propose CigaR, the first LLM-based APR tool that focuses on minimizing the repair cost. CigaR works in two major steps: generating a first plausible patch and multiplying plausible patches. CigaR optimizes the prompts and the prompt setting to maximize the information given to LLMs using the smallest possible number of tokens. Our experiments on 429 bugs from the widely used Defects4J and HumanEval-Java datasets shows that CigaR reduces the token cost by 73%. On average, CigaR spends 127k tokens per bug while the baseline uses 467k tokens per bug. On the subset of bugs that are fixed by both, CigaR spends 20k per bug while the baseline uses 608k tokens, a cost saving of 96%. Our extensive experiments show that CigaR is a cost-effective LLM-based program repair tool that uses a low number of tokens to automatically generate patches.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Adversarial Reasoning for Repair Based on Inferred Program Intent

    cs.SE 2025-05 conditional novelty 7.0 of 10

    AdverIntent-Agent infers multiple adversarial program intents, generates tests for each, and produces patches, correctly repairing 77 Defects4J and 105 HumanEval-Java bugs.

  2. OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution

    cs.SE 2025-05 conditional novelty 6.0 of 10

    OmniGIRL introduces a 959-instance multilingual, multimodal GitHub issue resolution benchmark; the best result, GPT-4o with Agentless-X, resolves only 8.6% of issues.

  3. VeCoGen: Automating Generation of Formally Verified C Code with Large Language Models

    cs.SE 2024-11 conditional novelty 6.0 of 10

    VeCoGen automatically generates and formally verifies loop-free C functions from ACSL and natural language specifications, solving 13 of 15 Codeforces problems with its default model.

  4. Automated Repair of C Programs Using Large Language Models

    cs.SE 2025-09 conditional novelty 5.0 of 10

    An agent that combines spectrum-based fault localization, test feedback, and chain-of-thought prompting repairs 44.93% of 3,902 Codeflaws C bugs, a 3.61-point gain over GPT-4 with CoT.

  5. The Art of Repair: Optimizing Iterative Program Repair with Instruction-Tuned Models

    cs.SE 2025-05 conditional novelty 5.0 of 10

    Using only 1,000 fine-tuning examples with full fine-tuning improves the number of plausible repairs by up to 78%, and iterative generation strategies help base models most on complex benchmarks like Defects4J.

  6. Assessing Large Language Models in Comprehending and Verifying Concurrent Programs across Memory Models

    cs.SE 2025-01 conditional novelty 5.0 of 10

    Five LLMs, including GPT-4, handle many simple concurrency checks but cannot reliably verify small programs under TSO and PSO relaxed memory models.

  7. LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities

    cs.SE 2026-01 unverdicted novelty 2.0 of 10

    A survey of LLM-based multi-agent systems across the software development life cycle, plus a research agenda for orchestration, human coordination, cost, and data.

Pith tools