The Thousand-Graph Hypothesis: A Testable Hypothesis of Task-Conditioned Relation Materialization in Repository-Level Code Reasoning

• URL: http://arxiv.org/abs/2608.26602v1
• Date: Thu, 27 Aug 2026 04:33:48 GMT
• Title: The Thousand-Graph Hypothesis: A Testable Hypothesis of Task-Conditioned Relation Materialization in Repository-Level Code Reasoning
• Abstract summary: Training repository knowledge into models is costly and quickly stale, while local retrieval can miss scattered requirements.<n>We propose an entity-only external interface with task-conditioned relation materialization during inference.
• Score: 2.7787094635105185
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Large software repositories are often beyond model context limits. Training repository knowledge into models is costly and quickly stale, while local retrieval can miss scattered requirements, and explicit relation graphs add ongoing maintenance burden. We propose an entity-only external interface with task-conditioned relation materialization during inference. A two-layer index separates global routing from local entity focus and is evaluated on DeepSeek-V4-Flash and SWE-bench Verified. The base, one-layer, and two-layer conditions achieve 92.1%, 94.2%, and 95.6% success, respectively, under zero pre-built entity-relation edges.

Related papers

• xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems [57.62172039072062]
  We introduce xDailyBench, a benchmark of 248 carefully curated tasks spanning 51 scenarios across personal life, white-collar work, learning and research, and cross-domain activities.<n>The tasks are grounded in requests that users have actually completed or genuinely intended to accomplish with AI, and are evaluated with fine-grained binary rubrics covering both explicit and implicit requirements.<n>The best models achieve a task-level score of 75.6%, while all models perform substantially worse on implicit than explicit requirements, with gaps no less than 9 percentage points.
  arXiv  Detail & Related papers  (2026-09-07T17:30:58Z)
• Cost-Effective Repository Exploration for Agentic Issue Localization [0.2715382584771446]
  We study whether this stage can be delegated to lower-cost models.<n>We measure early candidate discovery, top-three gold-file coverage, strict file-set recovery, agent time, and token usage.<n>Highest-quality explorer leads across localization metrics, but substantially cheaper operating points emerge.
  arXiv  Detail & Related papers  (2026-08-30T09:16:33Z)
• DREA: Decoupled Reasoning and Exploration Agents for Repository-Level Vulnerability Detection [16.007199928732614]
  We present DREA, a hypothesis-driven framework for repository-level vulnerability detection.<n>Goal-directed context acquisition is the primary source of detection improvement in this design.<n>To support evaluation, we construct RepoPairBench, a repository-grounded benchmark of validated Python vulnerability-fix pairs from real-world projects.
  arXiv  Detail & Related papers  (2026-07-15T04:49:05Z)
• RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations [51.43574078961796]
  We introduce RepoMirage, a two-stage evaluation suite built on SWE-Bench Verified.<n>RepoMirage-Perturb applies three types of semantics-preserving repository-level perturbations, revealing a clear performance drop when correct solving requires broader context access.<n>We propose RepoAnchor, a structure-first prototype workflow that separates repository exploration from downstream problem solving.
  arXiv  Detail & Related papers  (2026-05-25T06:26:43Z)
• ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox [61.862814740220806]
  $textbfComplexMCP$ is a benchmark designed to evaluate agents in rigorous conditions.<n>Built on the Model Context Protocol (MCP), $textbfComplexMCP$ provides over 300 meticulously tested tools.
  arXiv  Detail & Related papers  (2026-05-11T16:20:51Z)
• Faithfulness-QA: A Counterfactual Entity Substitution Dataset for Training Context-Faithful RAG Models [13.478990954968316]
  Retrieval-Augmented Generation models produce answers grounded in parametric memory rather than the retrieved context.<n>We introduce Faithfulness-QA, a large-scale dataset of 99,094 samples constructed through counterfactual entity substitution.
  arXiv  Detail & Related papers  (2026-04-28T07:21:46Z)
• CCTU: A Benchmark for Tool Use under Complex Constraints [66.87622847854337]
  We introduce CCTU, a benchmark for evaluating large language models (LLMs) under complex constraints.<n>The benchmark comprises 200 carefully curated and challenging test cases across diverse tool-use scenarios.<n>We develop an executable constraint validation module that performs step-level validation and enforces compliance.
  arXiv  Detail & Related papers  (2026-03-16T14:05:13Z)
• Beyond Memorization: Reasoning-Driven Synthesis as a Mitigation Strategy Against Benchmark Contamination [77.69093448529455]
  We present an empirical study using an infinitely scalable framework to synthesize research-level QA directly from arXiv papers.<n>We evaluate a lack of significant performance decay near knowledge cutoff dates for models of various sizes, developers, and release dates.<n>We hypothesize that the multi-step reasoning required by our synthesis pipeline offered additional complexity that goes deeper than shallow memorization.
  arXiv  Detail & Related papers  (2025-08-26T16:41:37Z)
• OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks [52.87238755666243]
  We present OmniEAR, a framework for evaluating how language models reason about physical interactions, tool usage, and multi-agent coordination in embodied tasks.<n>We model continuous physical properties and complex spatial relationships across 1,500 scenarios spanning household and industrial domains.<n>Our systematic evaluation reveals severe performance degradation when models must reason from constraints.
  arXiv  Detail & Related papers  (2025-08-07T17:54:15Z)
• A theoretical framework for self-supervised contrastive learning for continuous dependent data [79.62732169706054]
  Self-supervised learning (SSL) has emerged as a powerful approach to learning representations, particularly in the field of computer vision.<n>We propose a novel theoretical framework for contrastive SSL tailored to emphsemantic independence between samples.<n>Specifically, we outperform TS2Vec on the standard UEA and UCR benchmarks, with accuracy improvements of $4.17$% and $2.08$%, respectively.
  arXiv  Detail & Related papers  (2025-06-11T14:23:47Z)
• A Frustratingly Easy Approach for Entity and Relation Extraction [25.797992240847833]
  We present a simple pipelined approach for entity and relation extraction. We establish the new state-of-the-art on standard benchmarks (ACE04, ACE05 and SciERC) Our approach essentially builds on two independent encoders and merely uses the entity model to construct the input for the relation model.
  arXiv  Detail & Related papers  (2020-10-24T07:14:01Z)

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.