Papers › Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution...

Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step

25 Feb 2024arXiv:2402.16906archive 2025-07-28

Li Zhong, Zilong Wang, Jingbo Shang

Large language models (LLMs) are leading significant progress in code generation. Beyond one-pass code generation, recent works further integrate unit tests and program verifiers into LLMs to iteratively refine the generated programs. However, these works consider the generated programs as an indivisible entity, which falls short for LLMs in debugging the programs, especially when the programs contain complex logic flows and data operations. In contrast, when human developers debug programs, they typically set breakpoints and selectively examine runtime execution information. The execution flow and the intermediate variables play a crucial role in the debugging process, yet they are underutilized in the existing literature on code generation. In this study, we introduce Large Language Model Debugger (LDB), a novel debugging framework that enables LLMs to refine their generated programs with the runtime execution information. Specifically, LDB segments the programs into basic blocks and tracks the values of intermediate variables after each block throughout the runtime execution. This allows LLMs to concentrate on simpler code units within the overall execution flow, verify their correctness against the task description block by block, and efficiently pinpoint any potential errors. Experiments demonstrate that LDB consistently enhances the baseline performance by up to 9.8% across the HumanEval, MBPP, and TransCoder benchmarks, archiving new state-of-the-art performance in code debugging for various LLM selections.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2402.16906")

Code

Syntology Ran 8 of 12 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 8 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

floridsleeves/llmdebugger officialmentioned in papermentioned on GitHubApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested; 8 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

8ran
4unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from floridsleeves/llmdebugger. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

add_code_block floridsleeves/llmdebugger/programming/generators/parse.py official repository ran fingerprinted Apache-2.0 (permissive) · 8eef2232a5acc7f9 · report
fix_func_impl_comments floridsleeves/llmdebugger/programming/utils.py official repository ran Apache-2.0 (permissive) · e2c95b0b2c04dbcf · report
function_with_timeout floridsleeves/llmdebugger/programming/executors/executor_utils.py official repository ran Apache-2.0 (permissive) · 21ce1caad7419f74 · report
get_output floridsleeves/llmdebugger/programming/executors/py_executor.py official repository ran Apache-2.0 (permissive) · a29cddda11d00bfe · report
insert_comment floridsleeves/llmdebugger/programming/utils.py official repository ran fingerprinted Apache-2.0 (permissive) · 42393bbefa5a1cd7 · report
parse_code_block floridsleeves/llmdebugger/programming/generators/parse.py official repository ran Apache-2.0 (permissive) · b4401818078b6b05 · report
parse_first_func floridsleeves/llmdebugger/programming/generators/parse.py official repository ran Apache-2.0 (permissive) · 276cbea7969c5ddd · report
prepare_function_from_seed floridsleeves/llmdebugger/programming/utils.py official repository ran Apache-2.0 (permissive) · f23c44a8032805cd · report
get_call_str floridsleeves/llmdebugger/programming/executors/py_executor.py official repository unverified Apache-2.0 (permissive) · 893d75cf140dbc4b · report
gpt_completion floridsleeves/llmdebugger/programming/generators/model.py official repository unverified Apache-2.0 (permissive) · e755ffd0c5efc22b · report
message_to_str floridsleeves/llmdebugger/programming/generators/model.py official repository unverified Apache-2.0 (permissive) · a067a230397d97aa · report
messages_to_str floridsleeves/llmdebugger/programming/generators/model.py official repository unverified Apache-2.0 (permissive) · 4e0f76b9ec8bd13a · report

Tasks

Code GenerationHumanEvalLanguage ModelingLanguage ModellingLarge Language Model

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Code Generation HumanEval LLaMA 3 Pass@1 99.4 #2 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections