Exploration Structure in LLM Agents for Multi-File Change Localization

• URL: http://arxiv.org/abs/2606.11976v1
• Date: Wed, 10 Jun 2026 11:54:14 GMT
• Title: Exploration Structure in LLM Agents for Multi-File Change Localization
• Abstract summary: Most AI agents explore repositories linearly, that is, visiting one directory or file per step.<n>We compare linear sequential exploration against non-linear, domain-scoped parallel agentic exploration.<n>We construct an approach for persistent-session evaluation of GitHub issues anchored at a single base commit.
• Score: 7.536387580547836
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repositories linearly, that is, visiting one directory or file per step. We postulate that this is a structural mismatch for changes that span several subsystems. We compare linear sequential exploration against non-linear, domain-scoped parallel agentic exploration. Using SWE Bench Pro as initial benchmark, we focus on ansible as an exemplar. We construct an approach for persistent-session evaluation of GitHub issues anchored at a single base commit. We compare our non-linear domain-agent file traversal system against a base LLM without direct repository access, a single agent Recursive Language Model (RLM) baseline with a persistent Python REPL and an external CLI baseline using Codex 5.5 High. Domain scoped parallel agent spawning with a small Haiku-class model achieves the highest micro F1 among Haiku class models by a large margin. Domain-agents is the second highest behind only the much larger Codex 5.5 High on our own expanded benchmark including over more recent PRs from 2025 and 2026. On the original, curated, 2020 SWE-bench Pro benchmark, a larger Sonnet plain LLM baseline attains higher micro F1 by predicting few files, leading to higher precision, but at significantly lower all gold recall. We also present three additional findings. First, documentation evolution is a latent dependency unresolved by any approach. Second, naive file system access can degrade localization driven by test-file over prediction. Lastly, forced multi-agent consultation does not measurably help and raises token cost substantially.

Related papers

• Baselines Before Architecture: Evaluating Coding Agents for Autonomous Penetration Testing [0.0]
  This paper presents a controlled study on the 104-task XBOW benchmark using default coding CLI agents as plain-agent baselines.<n>We first run Codex, OpenCode, and Pi with the same GPT-5 model, budget, target interface, and scoring rule.<n>We then compare the default Codex scaffold with published MAPTA and PentestGPT V2 results under the closest available model matches.
  arXiv  Detail & Related papers  (2026-07-13T13:31:46Z)
• ChipMATE: Multi-Agent Training via Reinforcement Learning for Enhanced RTL Generation [55.947962672433675]
  ChipMATE is the first self-trained multi-agent framework for RTL generation.<n>Inspired by industrial practice, ChipMATE pairs a Verilog agent with a Python reference-model agent that mutually verify each other's outputs.<n>ChipMATE achieves 75.0% and 80.1% pass@1 on VerilogEval V2 with 4B and 9B base models.
  arXiv  Detail & Related papers  (2026-05-13T01:04:21Z)
• LARGER: Lexically Anchored Repository Graph Exploration and Retrieval [9.90137784523552]
  repository-level coding agents must first localize the files and symbols relevant to a task.<n>Existing approaches often require separate graph tools or stages that fragment the agent's interaction loop.<n>We introduce LARGER, a lexically anchored active-set retrieval framework that starts from lexical matches, aligns them to graph anchors, and performs confidence-filtered local expansion within the agent's existing search loop.
  arXiv  Detail & Related papers  (2026-05-08T05:03:46Z)
• Leveraging LLMs for Multi-File DSL Code Generation: An Industrial Case Study [39.936784974007644]
  Large language models (LLMs) perform strongly on general-purpose code generation, yet their applicability to enterprise domain-specific languages (s) remains underexplored.<n>We report an industrial case study at BMW that adapts code-oriented LLMs to generate and modify project-root DSL artifacts for an Xtext-based DSL.<n>We encode as structured, path-response generation at repository scale and learning cross-file dependencies.
  arXiv  Detail & Related papers  (2026-04-27T16:38:01Z)
• Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration [57.23877089929136]
  Graph-of-Agents (GoA) is a new graph-based framework for modeling multi-agent LLM communication.<n>GoA achieves superior performance using only 3 selected agents, outperforming recent multi-agent LLM baselines.
  arXiv  Detail & Related papers  (2026-04-18T21:13:03Z)
• MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning [74.07254720088926]
  We introduce MM-Doc-R1, a novel framework that employs an agentic, vision-aware workflow to address long document visual question answering.<n>We propose Similarity-based Policy Optimization (SPO), addressing baseline estimation bias in existing multi-turn reinforcement learning (RL) algorithms like GRPO.<n>Our experiments on the MMLongbench-Doc benchmark show that MM-Doc-R1 outperforms previous baselines by 10.4%.
  arXiv  Detail & Related papers  (2026-04-15T07:39:08Z)
• AutoMLGen: Navigating Fine-Grained Optimization for Coding Agents [27.864519204078004]
  Large language models (LLMs) have shown impressive performance in general programming tasks.<n>We introduce AutoMLGen, an LLM-based coding agent that integrates a domain knowledge base for high-quality prior guidance.<n>We show that AutoMLGen achieves state-of-the-art performance in numerous dimensions, such as the average medal rate and the valid submission rate.
  arXiv  Detail & Related papers  (2025-10-09T17:45:05Z)
• Rethinking Reward Models for Multi-Domain Test-Time Scaling [91.76069784586149]
  Prior work generally assumes that process reward models (PRMs) outperform outcome reward models (ORMs) that assess only the final answer.<n>We present the first unified evaluation of four reward model variants across 14 diverse domains.<n>We attribute this to PRM-style stepwise scoring, which inherits label noise from LLM auto-labeling and has difficulty evaluating long reasoning trajectories.
  arXiv  Detail & Related papers  (2025-10-01T04:21:14Z)
• Teamwork makes the dream work: LLMs-Based Agents for GitHub README.MD Summarization [7.330697128881243]
  We propose Metagente as a novel approach to amplify the synergy of various Large Language Models (LLMs)<n>Metagente is a Multi-Agent framework based on a series of LLMs to self-optimize the system through evaluation, feedback, and cooperation among specialized agents.<n>The performance gain compared to GitSum, the most relevant benchmark, ranges from 27.63% to 60.43%.
  arXiv  Detail & Related papers  (2025-03-13T20:42:39Z)
• Reinforcement Learning for Long-Horizon Interactive LLM Agents [56.9860859585028]
  Interactive digital agents (IDAs) leverage APIs of stateful digital environments to perform tasks in response to user requests.<n>We present a reinforcement learning (RL) approach that trains IDAs directly in their target environments.<n>We derive LOOP, a data- and memory-efficient variant of proximal policy optimization.
  arXiv  Detail & Related papers  (2025-02-03T18:35:42Z)
• Autonomous Legacy Web Application Upgrades Using a Multi-Agent System [3.456157428615978]
  Large Language Models (LLMs) for autonomous code generation is gaining attention in emerging technologies.<n>Many outdated web applications pose security and reliability challenges, yet companies continue using them due to the complexity and cost of upgrades.<n>We propose an LLM-based multi-agent system that autonomously upgrades legacy web applications to the latest versions.
  arXiv  Detail & Related papers  (2025-01-31T15:14:14Z)
• SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution [56.9361004704428]
  Large Language Models (LLMs) have demonstrated remarkable proficiency across a variety of complex tasks.<n>SWE-Fixer is a novel open-source framework designed to effectively and efficiently resolve GitHub issues.<n>We assess our approach on the SWE-Bench Lite and Verified benchmarks, achieving competitive performance among open-source models.
  arXiv  Detail & Related papers  (2025-01-09T07:54:24Z)

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.