# MARCO: Meta-Reflection with Cross-Referencing for Code Reasoning

arXiv: https://arxiv.org/abs/2505.17481 · HTML: https://mlsanity.com/paper/2505.17481/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 44 of its 80 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 30 of 44)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [CodeT5+: Open Code Large Language Models for Code Understanding and Generation](https://mlsanity.com/paper/2305.07922/) (2023)
- [CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution](https://mlsanity.com/paper/2401.03065/) (2024)
- [DeepCoder: Learning to Write Programs](https://mlsanity.com/paper/1611.01989/) (2016)
- [Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step](https://mlsanity.com/paper/2402.16906/) (2024)
- [Chain of Code: Reasoning with a Language Model-Augmented Code Emulator](https://mlsanity.com/paper/2312.04474/) (2023)
- [SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs](https://mlsanity.com/paper/2502.12134/) (2025)
- [Forest-of-Thought: Scaling Test-Time Compute for Enhancing LLM Reasoning](https://mlsanity.com/paper/2412.09078/) (2024)
- [Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement](https://mlsanity.com/paper/2310.08559/) (2023)
- [Towards Mitigating Hallucination in Large Language Models via Self-Reflection](https://mlsanity.com/paper/2310.06271/) (2023)
- [DebugBench: Evaluating Debugging Capability of Large Language Models](https://mlsanity.com/paper/2401.04621/) (2024)
- [MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models](https://mlsanity.com/paper/2308.09729/) (2023)
- [Interpretable Contrastive Monte Carlo Tree Search Reasoning](https://mlsanity.com/paper/2410.01707/) (2024)
- [Demystifying Chains, Trees, and Graphs of Thoughts](https://mlsanity.com/paper/2401.14295/) (2024)
- [Reasoning Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling](https://mlsanity.com/paper/2408.17017/) (2024)
- [Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs](https://mlsanity.com/paper/2404.15676/) (2024)
- [LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning](https://mlsanity.com/paper/2407.02511/) (2024)
- [A Survey on Evaluating Large Language Models in Code Generation Tasks](https://mlsanity.com/paper/2408.16498/) (2024)
- [Dynamic Parallel Tree Search for Efficient LLM Reasoning](https://mlsanity.com/paper/2502.16235/) (2025)
- [Boosting Logical Reasoning in Large Language Models through a New Framework: The Graph of Thought](https://mlsanity.com/paper/2308.08614/) (2023)
- [Self-Reflection in LLM Agents: Effects on Problem-Solving Performance](https://mlsanity.com/paper/2405.06682/) (2024)
- [DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy](https://mlsanity.com/paper/2310.18659/) (2023)

## Abstract (arXiv)

The ability to reason is one of the most fundamental capabilities of large language models (LLMs), enabling a wide range of downstream tasks through sophisticated problem-solving. A critical aspect of this is code reasoning, which involves logical reasoning with formal languages (i.e., programming code). In this paper, we enhance this capability of LLMs by exploring the following question: how can an LLM agent become progressively smarter in code reasoning with each solution it proposes, thereby achieving substantial cumulative improvement? Most existing research takes a static perspective, focusing on isolated problem-solving using frozen LLMs. In contrast, we adopt a cognitive-evolving perspective and propose a novel framework named Meta-Reflection with Cross-Referencing (MARCO) that enables the LLM to evolve dynamically during inference through self-improvement. From the perspective of human cognitive development, we leverage both knowledge accumulation and lesson sharing. In particular, to accumulate knowledge during problem-solving, we propose meta-reflection that reflects on the reasoning paths of the current problem to obtain knowledge and experience for future consideration. Moreover, to effectively utilize the lessons from other agents, we propose cross-referencing that incorporates the solution and feedback from other agents into the current problem-solving process. We conduct experiments across various datasets in code reasoning, and the results demonstrate the effectiveness of MARCO.