AI Paper Atlas

Research map / Multi-agent systems and games / LLM agents

RECoRD: A Multi-Agent LLM Framework for Reverse Engineering Codebase to Relational Diagram

Yuan Xue, Xiaoyu Lu, Yunfei Bai, Yunan Liu, Hoiyi Ng

AAAI 2026 · Multi-agent systems and games › LLM agents · approach: Robust and efficient agent execution · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes RECoRD, a multi-agent LLM framework that reverse engineers codebases into relational diagrams to expose interpretable causal structure of algorithms.

Problem

Reverse engineering complex algorithms in industrial codebases into interpretable causal structures; the potential of LLMs for this task is unexplored.

Approach

A multi-agent LLM framework (RECoRD) that converts code into relational diagrams capturing the algorithm's logical and causal structure, leveraging LLM code understanding.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
apply DPO reinforcement fine-tuning with LoRA (ablation)Phi-4 · MiniSCOT (full entity list)relation F1: 0.690 -> 0.968Improved
apply DPO reinforcement fine-tuning with LoRA (ablation)Qwen-7B-Instruct · Newsvendor (full entity list)relation F1: 0.810 -> 0.895Improved
apply DPO reinforcement fine-tuning with LoRA (ablation)Phi-4 · Newsvendor (LLM+H+AST entities)relation F1: 0.647 -> 0.647No clear effect
apply DPO reinforcement fine-tuning with LoRA (ablation)Phi-4 · Black-Scholes (full entity list)relation F1: 0.556 -> 0.562No clear effect
apply DPO reinforcement fine-tuning with LoRA (ablation)Qwen-14B-Instruct · Black-Scholes (LLM+H+AST entities)relation F1: 0.483 -> 0.569Improved
fine-tune on News Vendor then transfer (ablation)Qwen2.5-7B-Instruct · MiniSCOT (full entity list)relation F1: 0.786 -> 0.857Improved
fine-tune on News Vendor then transfer (ablation)Phi-4 · MiniSCOT (LLM+H entities)relation F1: 0.121 -> 0.250Improved
use noisier LLM+H entity list instead of full ground-truth entity list (ablation)RECoRD RFT · MiniSCOTrelation F1: 0.968 -> 0.467Hurt
add human filtering to AST+code entity extraction (ablation)entity extraction agent · MiniSCOTentity precision: 0.56 -> 0.83Improved
add human filtering to AST+code entity extraction (ablation)entity extraction agent · Newsvendorentity precision and recall: 0.89/0.73 -> 0.89/0.73No clear effect
add AST guidance to code-only entity extraction (ablation)entity extraction agent · Black-Scholesentity recall: 0.21 -> 0.58Improved
use AST guidance instead of code-only entity extraction (ablation)entity extraction agent · Newsvendorentity precision: 1.00 -> 0.89Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy