Imitation Game: Reproducing Deep Learning Bugs Leveraging an Intelligent Agent

Mehil B Shah, Mohammad Masudur Rahman, Foutse Khomh · Dec 17, 2025 · Citations: 0

Abstract

Despite their wide adoption in various domains (e.g., healthcare, finance, software engineering), Deep Learning (DL)-based applications suffer from many bugs, failures, and vulnerabilities. Reproducing these bugs is essential for their resolution, but it is extremely challenging due to the inherent nondeterminism of DL models and their tight coupling with hardware and software environments. According to recent studies, only about 3% of DL bugs can be reliably reproduced using manual approaches. To address these challenges, we present RepGen, a novel, automated, and intelligent approach for reproducing deep learning bugs. RepGen constructs a learning-enhanced context from a project, develops a comprehensive plan for bug reproduction, employs an iterative generate-validate-refine mechanism, and thus generates such code using an LLM that reproduces the bug at hand. We evaluate RepGen on 106 real-world deep learning bugs and achieve a reproduction rate of 80.19%, a 19.81% improvement over the state-of-the-art measure. A developer study involving 27 participants shows that RepGen improves the success rate of DL bug reproduction by 23.35%, reduces the time to reproduce by 56.8%, and lowers participants' cognitive load.

HFEPX Relevance Assessment

This paper appears adjacent to HFEPX scope (human-feedback/eval), but does not show strong direct protocol evidence in metadata/abstract.

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Unknown
Expertise required: Coding
Extraction source: Persisted extraction

Evaluation Lens

Evaluation modes: Automatic Metrics
Agentic eval: None
Quality controls: Not reported
Confidence: 0.35
Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

success rate

Research Brief

Deterministic synthesis

According to recent studies, only about 3% of DL bugs can be reliably reproduced using manual approaches. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 3, 2026, 6:49 PM · Grounded in abstract + metadata only

Key Takeaways

According to recent studies, only about 3% of DL bugs can be reliably reproduced using manual approaches.
To address these challenges, we present RepGen, a novel, automated, and intelligent approach for reproducing deep learning bugs.
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher Actions

Treat this as method context, then pivot to protocol-specific HFEPX hubs.
Identify benchmark choices from full text before operationalizing conclusions.
Validate metric comparability (success rate).

Caveats

Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
Low-signal flag detected: protocol relevance may be indirect.

Recommended Queries

human-eval protocol design pairwise preference data quality inter-rater agreement adjudication

Research Summary

Contribution Summary

According to recent studies, only about 3% of DL bugs can be reliably reproduced using manual approaches.
To address these challenges, we present RepGen, a novel, automated, and intelligent approach for reproducing deep learning bugs.
We evaluate RepGen on 106 real-world deep learning bugs and achieve a reproduction rate of 80.19%, a 19.81% improvement over the state-of-the-art measure.

Why It Matters For Eval

Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Researcher Checklist

Gap: Human feedback protocol is explicit

No explicit human feedback protocol detected.
Pass: Evaluation mode is explicit

Detected: Automatic Metrics
Gap: Quality control reporting appears

No calibration/adjudication/IAA control explicitly detected.
Gap: Benchmark or dataset anchors are present

No benchmark/dataset anchor extracted from abstract.
Pass: Metric reporting is present

Detected: success rate

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

SkillCraft: Can LLM Agents Learn to Use Tools Skillfully? Category Neighbor

Citations: 0 Relevance: 3.75
- Shared arXiv category (cs.SE)
- Shared metric mentions
- Shared terminology (success, rate, agent)
MoDora: Tree-Based Semi-Structured Document Analysis System Category Neighbor

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.AI, cs.LG)
pMoE: Prompting Diverse Experts Together Wins More in Visual Adaptation Category Neighbor

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.AI, cs.LG)
Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning Category Neighbor

Citations: 0 Relevance: 3.20
- Shared arXiv category (cs.AI, cs.LG)
AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning Category Neighbor

Citations: 0 Relevance: 2.50
- Shared arXiv category (cs.AI)
- Shared terminology (leveraging, agent)
Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.LG)
- Shared terminology (agent)
Modeling Expert AI Diagnostic Alignment via Immutable Inference Snapshots Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.AI)
- Shared terminology (rate)
ReCoN-Ipsundrum: An Inspectable Recurrent Persistence Loop Agent with Affect-Coupled Control and Mechanism-Linked Consciousness Indicator Assays Category Neighbor

Citations: 0 Relevance: 2.05
- Shared arXiv category (cs.AI)
- Shared terminology (agent)

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote