# Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs

arXiv: https://arxiv.org/abs/2508.07434 · HTML: https://mlsanity.com/paper/2508.07434/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- First posted on arXiv 10 Aug 2025.

## Placed in

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

## Built on by (most cited first, 7 of 7)

- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System](https://mlsanity.com/paper/2510.09721/) (2025)
- [Controlled Self-Evolution for Algorithmic Code Optimization](https://mlsanity.com/paper/2601.07348/) (2026)
- [Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding](https://mlsanity.com/paper/2601.21969/) (2026)
- [MIND-Skill: Quality-Guaranteed Skill Generation via Multi-Agent Induction and Deduction](https://mlsanity.com/paper/2605.08670/) (2026)
- [AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories](https://mlsanity.com/paper/2609.05837/) (2026)
- [Online Causal Kalman Filtering for Stable and Effective Policy Optimization](https://mlsanity.com/paper/2602.10609/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) with inference-time scaling techniques show promise for code generation, yet face notable efficiency and scalability challenges. Construction-based tree-search methods suffer from rapid growth in tree size, high token consumption, and lack of anytime property. In contrast, improvement-based methods offer better performance but often struggle with uninformative reward signals and inefficient search strategies. In this work, we propose ReLoc, a unified local search framework which effectively performs step-by-step code revision. Specifically, ReLoc explores a series of local revisions through four key algorithmic components: initial code drafting, neighborhood code generation, candidate evaluation, and incumbent code updating, each of which can be instantiated with specific decision rules to realize different local search algorithms such as Hill Climbing (HC) or Genetic Algorithm (GA). Furthermore, we develop a specialized revision reward model that evaluates code quality based on revision distance to produce fine-grained preferences that guide the local search toward more promising candidates. Finally, our extensive experimental results demonstrate that our approach achieves superior performance across diverse code generation tasks, significantly outperforming both construction-based tree search as well as the state-of-the-art improvement-based code generation methods.