The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks

• URL: http://arxiv.org/abs/2608.16630v1
• Date: Mon, 17 Aug 2026 14:30:41 GMT
• Title: The Working Set of a Coding Agent: Coherence Debt in Repository-Scale Tasks
• Abstract summary: Repository-scale coding requires an agent to keep tests, imports, configuration, and migration rules consistent within a bounded context window.<n>We supply and withhold each channel and inject faults across seven models and five harnesses.<n>When a rename defeats what models memorized about a real library, all seven fail in the same place, passing and missing the same tests.
• Score: 14.070053515623883
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Repository-scale coding requires an agent to keep tests, imports, configuration, and migration rules consistent within a bounded context window. We model this as reconstructing a coupled-fact graph: at each edit, a required fact comes from recent context or parametric memory, and the facts covered by neither form coherence debt. We supply and withhold each channel and inject faults across seven models and five harnesses. As expected, no model completes a task on an unseen API with both channels empty, and putting the facts in the prompt restores success. When a rename defeats what models memorized about a real library, all seven fail in the same place, passing and missing the same tests. Availability decides the outcome and distance does not: withholding a fact costs exactly the work it supports, and a supplied fact works as well far from the edit as next to it. Harnesses pay unequal prices for it: configurations that all pass every test differ more than tenfold in tokens consumed because they rebuild the same content at different rates, and spending more recovers nothing when facts are withheld. A missing fact produces wrong work rather than absent work: an agent asked to act acts, fabricating the file or guessing the value, so instruments built on reads look for a hole already filled. How often it says it is blocked instead is a property of the model, from every trial to none. Availability does not settle every edit: where standard and code disagree, agents follow the standard even when it prescribes the worse code, so a stale convention file costs more than no file. Because parametric memory substitutes for reading, on SWE-bench, where models likely know the repositories, reads no longer predict success. Harnesses should keep the facts an edit depends on available when the agent writes, and check that availability against what the agent produces rather than what it reads.

Related papers

• SkillGLoW: Procedural-Family Skill Consolidation for Self-Improving Agents on Long-Horizon Task Streams [55.90739575113059]
  We argue the missing unit of reuse is the solving procedure shared by a cluster of related tasks, and build SkillGLoW around it.<n>Across four benchmarks (mathematical reasoning, terminal automation, software repair, and embodied control) and three models, the priors gain 17.2 points (hard) over the no-skill baseline on average.
  arXiv  Detail & Related papers  (2026-09-02T07:31:18Z)
• Belief-Calibrated Optimization: An Explicit World Model for Agentic Optimization [31.31831511580543]
  We introduce Belief-Calibrated Optimization (BCO), a method that writes that belief down as a persistent in-context document.<n>A fresh predictor given the accumulated document forecasts how the environment will respond more accurately than given either no document or a same-form copy whose content has been falsified.
  arXiv  Detail & Related papers  (2026-09-01T20:47:04Z)
• SpecPath: Testing Coding Agents Across Contract-Equivalent Specification Histories [13.437222222971272]
  We identify specification-path sensitivity, a failure mode in which requirement histories that are equivalent in their final meaning lead the same agent system to produce behaviorally different programs.<n>We introduce SpecPath, a diagnostic evaluation that holds the repository, final contract, verifier, agent system, and execution budget fixed while changing only the revision path that leads to the contract.
  arXiv  Detail & Related papers  (2026-08-10T16:19:00Z)
• Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction [57.138342889101345]
  Tencent WorkBuddy Bench is a multi-domain evaluation suite for coding agents.<n>This report documents its construction methodology, scoring protocol, and a cross-model leaderboard.
  arXiv  Detail & Related papers  (2026-07-23T04:34:06Z)
• TRACE: An Operational Reasoning Schema for Auditable Agentic Commitments [0.0]
  TRACE (Typed Reasoning And Commitment Evidence) is a typed, versioned schema for recording reasoning traces.<n>The paper argues in three layers that reasoning is not in the language model.<n>A record-consumer contract states what a record guarantees and what a consumer must honor in return.
  arXiv  Detail & Related papers  (2026-07-14T08:08:21Z)
• RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications [0.0]
  RuBench 1.0 is a benchmark of 25 tasks mined from recent fix commits in five live open-source repositories.<n>Each task is specified in Russian, written from scratch in the style of an actual customer request, not translated.<n>All 25 fix commits postdate the training-data cutoffs of every evaluated model.
  arXiv  Detail & Related papers  (2026-07-07T15:41:22Z)
• Can Code Specify a System Precisely Enough to Formally Verify It? [0.0]
  This paper evaluates both on production software: the payment workflow of an operational restaurant point-of-sale system.<n>The core protocol is correct relative to a hand-built, line-cited model under a precisely stated failure model.<n>A single probe of the production payment sandbox exposed a response-shape divergence that makes an entire recovery ladder unreachable.
  arXiv  Detail & Related papers  (2026-07-06T13:39:00Z)
• PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation [51.92442051257354]
  PairCoder improves essentially every benchmark whose artifact is verifiable, on full official metric suites rather than execution alone.<n>TikZ compile rate up 10 to 30 points on every model, at 2.9 to 9.2 times single model cost.
  arXiv  Detail & Related papers  (2026-07-02T08:36:02Z)
• PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise [60.63315470285562]
  MiniTruePrefixes is a novel specialized model that better detects factual inconsistencies over text prefixes.<n>We show that integrating MiniTruePrefixes into a controlled decoding framework substantially improves factual consistency in abstractive summarization.
  arXiv  Detail & Related papers  (2025-11-03T09:07:44Z)
• SolBench: A Dataset and Benchmark for Evaluating Functional Correctness in Solidity Code Completion and Repair [51.0686873716938]
  We introduce SolBench, a benchmark for evaluating the functional correctness of Solidity smart contracts generated by code completion models.<n>We propose a Retrieval-Augmented Code Repair framework to verify functional correctness of smart contracts.<n>Results show that code repair and retrieval techniques effectively enhance the correctness of smart contract completion while reducing computational costs.
  arXiv  Detail & Related papers  (2025-03-03T01:55:20Z)
• Studying Large Language Model Behaviors Under Context-Memory Conflicts With Real Documents [54.953320616069654]
  Retrieval-augmented generation mitigates many problems of fully parametric language models. In RAG, the model's knowledge can be updated from documents provided in context. We present a framework for studying such knowledge conflicts in a realistic setup.
  arXiv  Detail & Related papers  (2024-04-24T17:59:36Z)

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.