Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2

• URL: http://arxiv.org/abs/2603.20334v1
• Date: Fri, 20 Mar 2026 08:16:15 GMT
• Title: Procedural Refinement by LLM-driven Algorithmic Debugging for ARC-AGI-2
• Abstract summary: We propose a neuro-symbolic procedural refinement approach, Abduction-Based Procedural Refinement (ABPR)<n>ABPR couples an LLM with a meta-interpreter that materialises program execution into compact, declarative tree-structured traces.<n>Our experiments show that ABPR paired with Gemini-3-Flash a Pass@2 score of 56.67% even in a language in which contemporary LLMs typically underperform.
• Score: 10.013415375696557
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In complex code-generation tasks, conversation-based LLM code repair exhibits limited ability to recover from first-pass programming errors, as such code revisions are usually driven by LLMs' "plausible reasoning" rather than a formal, algorithmic debugging procedure. However, a formal foundation for such debugging exists in Udi Shapiro's theory of algorithmic program debugging (APD), which frames program repair as an explicit, stepwise procedural refinement process. In this paper, we propose a neuro-symbolic procedural refinement approach, Abduction-Based Procedural Refinement (ABPR), which couples an LLM with a meta-interpreter that materialises program execution into compact, declarative tree-structured traces, following the principles of APD. We evaluate ABPR on ARC-AGI-2, a benchmark requiring strong abstraction and debugging capabilities, and adopt Prolog as the target language due to its declarative semantics, which are well-suited to algorithmic program debugging. Our experiments show that ABPR paired with Gemini-3-Flash achieves a Pass@2 score of 56.67\% even in a language in which contemporary LLMs typically underperform. These results point towards a more auditable paradigm for program repair by integrating LLMs with classical formal methods.

Related papers

• The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis [50.473217152006875]
  MIMIC is a framework that leverages executable code as a rigorous medium for reasoning data synthesis.<n>MIMIC transforms algorithms into verifiable reasoning trajectories through narrative fusion, code-guided test synthesis, and dynamic code instrumentation.<n>Our method significantly elevates accuracy across general reasoning, complex mathematical benchmarks, and fine-grained deterministic tasks.
  arXiv  Detail & Related papers  (2026-09-13T17:04:16Z)
• Unlocking LLM Code Correction with Iterative Feedback Loops [5.504955093712013]
  This study introduces metrics to evaluate code failures, analyze rectification patterns, and compare the effectiveness of reasoning and non-reasoning models.<n>Results show that reasoning models consistently improve over iterations, substantially outperforming non-reasoning models in leveraging feedback.
  arXiv  Detail & Related papers  (2026-06-16T04:47:42Z)
• From I/O to Code with Discovery Agent [103.88427301265669]
  We propose DIO-Agent, a discovery agent for IO2Code.<n>Our method frames IO2Code as an evolutionary search over discrete program space.<n>Extensive experiments show that DIO-Agent consistently outperforms both traditional program-by-example method and SOTA evolution-agent baselines.
  arXiv  Detail & Related papers  (2026-05-14T18:57:32Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• InspectCoder: Dynamic Analysis-Enabled Self Repair through interactive LLM-Debugger Collaboration [71.18377595277018]
  Large Language Models (LLMs) frequently generate buggy code with complex logic errors that are challenging to diagnose.<n>We present InspectCoder, the first agentic program repair system that empowers LLMs to actively conduct dynamic analysis via interactive debugger control.
  arXiv  Detail & Related papers  (2025-10-21T06:26:29Z)
• Do AI models help produce verified bug fixes? [62.985237003585674]
  Large Language Models are used to produce corrections to software bugs.<n>This paper investigates how programmers use Large Language Models to complement their own skills.<n>The results are a first step towards a proper role for AI and LLMs in providing guaranteed-correct fixes to program bugs.
  arXiv  Detail & Related papers  (2025-07-21T17:30:16Z)
• Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs [13.708569727719434]
  Large Language Models (LLMs) show promising performance on various programming tasks.<n>We aim to remedy this potential blind spot by augmenting standard APR prompts with program execution traces.
  arXiv  Detail & Related papers  (2025-05-07T14:12:41Z)
• SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning [30.938876549335067]
  This paper presents SymRTLO, a novel neuron-symbolic RTL optimization framework.<n>A symbolic module is proposed for analyzing and optimizing finite state machine (FSM) logic.<n> Experiments on the RTL-Rewriter benchmark with Synopsys Design Compiler and Yosys show that SymRTLO improves power, performance, and area (PPA) by up to 43.9%, 62.5%, and 51.1%, respectively.
  arXiv  Detail & Related papers  (2025-04-14T16:15:55Z)
• Pragmatic Reasoning improves LLM Code Generation [34.01862911727194]
  Large Language Models (LLMs) have demonstrated impressive potential in translating natural language (NL) instructions into program code.<n>To address this challenge, researchers have proposed approaches that produce multiple candidates of the program code and then rerank them to identify the best solution.<n>We propose CodeRSA, a novel code candidate reranking mechanism built upon the Rational Speech Act (RSA) framework.
  arXiv  Detail & Related papers  (2025-02-20T12:44:26Z)
• Designing Algorithms Empowered by Language Models: An Analytical Framework, Case Studies, and Insights [86.06371692309972]
  This work presents an analytical framework for the design and analysis of large language models (LLMs)-based algorithms.<n>Our proposed framework serves as an attempt to mitigate such headaches.
  arXiv  Detail & Related papers  (2024-07-20T07:39:07Z)
• DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation [57.07295906718989]
  Constrained decoding approaches aim to control the meaning or style of text generated by pre-trained large language (Ms also PLMs) for various tasks at inference time.<n>These methods often guide plausible continuations by greedily and explicitly selecting targets.<n>Inspired by cognitive dual-process theory, we propose a novel decoding framework DECIDER.
  arXiv  Detail & Related papers  (2024-03-04T11:49:08Z)
• Fully Autonomous Programming with Large Language Models [0.9558392439655015]
  Current approaches to program synthesis with Large Language Models (LLMs) exhibit a "near miss syndrome" We use OpenAI Codex as the LLM and Program Synthesis Benchmark 2 as a database of problem descriptions and tests for evaluation. The resulting framework outperforms both conventional usage of Codex without the repair phase and traditional genetic programming approaches.
  arXiv  Detail & Related papers  (2023-04-20T16:12:05Z)

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.