Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study

• URL: http://arxiv.org/abs/2607.02436v1
• Date: Thu, 02 Jul 2026 17:08:21 GMT
• Title: Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study
• Abstract summary: 90 independent agent runs built the same application, a real time retrospective board, from one detailed specification.<n>The runs spanned several model generations, two agent harnesses, two reasoning effort levels, a testing tool, and two design oriented prompts.<n>The testing tool raised cost by 42 to 68 percent without improving functional score or reliability, even on interface visible criteria.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agentic coding assistants are increasingly given extra capabilities, such as browser based testing tools and design oriented system prompts, on the assumption that more capability yields better software. This study tested that assumption directly. Ninety independent agent runs built the same application, a real time retrospective board, from one detailed specification, each scored on a fixed 14 criterion functional rubric (42 point maximum) and a visual quality review. The runs spanned several model generations, two agent harnesses, two reasoning effort levels, a testing tool, and two design oriented prompts. Capability tier dominated: frontier models clustered near the ceiling while a low cost local model fell to 24 to 37 points. A criterion level analysis revealed what run totals conceal. Container deployment was the dominant defect, failing first try in 44 percent of runs, with its failure rate shifting sharply across model generations while mean totals moved less than a point. The testing tool raised cost by 42 to 68 percent without improving functional score or reliability, even on interface visible criteria. Raising reasoning effort from High to xHigh lifted first try perfect runs from 28 percent to 89 percent and cut corrective prompts about five fold, for 9 to 29 percent more cost. A design oriented prompt raised visual quality, 4.5 versus 3.0 on a 5 point scale, without lifting function, and a one paragraph paraphrase of its directive reproduced the entire lift. The practical lesson is to match the fix to the failure: most first run failures came from weak reasoning, which a stronger model or more effort prevents, not from visible flaws a checking tool would catch.

Related papers

• Determinants and Limits of LLM Security-Tool Orchestration: A Study with HexStrike-AI [2.2616066835313253]
  We run 86 picoCTF challenges across seven categories and three difficulty tiers, under three tool-access regimes and three model/client configurations.<n>We apply corrections to existing tools, agent-behavior changes, and eleven new capability tools, and re-run the previously-unsuccessful trials.<n>The overall solve rate rises from 55.4% to 72.0%, and every configuration improves significantly.
  arXiv  Detail & Related papers  (2026-07-03T02:20:04Z)
• Knowledge Index of Noah's Ark [63.143852586221534]
  We introduce KINA, an 899-item benchmark across 261 fine-grained disciplines.<n>We prove a bonus-on-bar tournament weakly FOSD-dominates flat payment in released-review quality.<n>The top model, Gemini-3.1-Pro-Preview, reaches 53.17%, followed by Claude-Opus-4.6 at 49.92% and GPT-5.4 at 48.55%.
  arXiv  Detail & Related papers  (2026-06-03T17:06:49Z)
• SPOQ: Specialist Orchestrated Queuing for Multi-Agent Software Engineering [2.0769172070951067]
  Multi-agent AI systems show promise for automating software engineering tasks.<n>Existing approaches suffer from coordination overhead, quality control gaps, and limited human oversight.<n>We introduce SPOQ (Specialist Orchestrated Queuing), a methodology combining three innovations.
  arXiv  Detail & Related papers  (2026-06-02T03:59:56Z)
• AgentAtlas: Beyond Outcome Leaderboards for LLM Agents [0.025718125188898048]
  AgentAtlas reframes agent evaluation as a diagnostic vocabulary and audit protocol.<n>The paper contributes: (i) a six-state control-decision taxonomy (Act / Ask / Refuse / Stop / Confirm / Recover); (ii) a trajectory-failure vocabulary with primary error source and downstream impact; and (iv) an illustrative protocol study on a synthetic 1,342-item set evaluated with eight models.
  arXiv  Detail & Related papers  (2026-05-19T22:05:12Z)
• KWBench: Measuring Unprompted Problem Recognition in Knowledge Work [0.0]
  KWBench is a benchmark for unprompted problem recognition in large language models.<n>It can identify a professional scenario before attempting to solve it.<n>It contains 223 tasks sourced from practitioners across acquisitions, contract negotiations, clinical pharmacy, organizational politics, fraud analysis, and incentive design.
  arXiv  Detail & Related papers  (2026-04-17T07:04:54Z)
• Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents [66.97968363332465]
  We introduce Claw-Eval, an end-to-end evaluation suite addressing all three gaps in agent benchmarks.<n>Claw-Eval comprises 300 human-verified tasks spanning 9 categories across three groups.<n>Every agent action is recorded through three independent evidence channels.
  arXiv  Detail & Related papers  (2026-04-07T17:43:18Z)
• SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks [55.76734816061826]
  We introduce SlopCodeBench, a language-agnostic benchmark comprising 20 problems and 93 checkpoints.<n>We track two trajectory-level quality signals: verbosity, the fraction of redundant or duplicated code, and structural erosion.<n>No agent solves any problem end-to-end across 11 models; the highest checkpoint solve rate is 17.2%.
  arXiv  Detail & Related papers  (2026-03-25T19:26:44Z)
• Capable but Unreliable: Canonical Path Deviation as a Causal Mechanism of Agent Failure in Long-Horizon Tasks [0.38991526486631006]
  We argue that many reliability failures are caused by drift from a task's latent solution structure, not capability failures.<n>We establish this causally using a natural experiment that holds model capability and task difficulty fixed by construction.
  arXiv  Detail & Related papers  (2026-02-22T02:37:57Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Benchmarking Reasoning Robustness in Large Language Models [76.79744000300363]
  We find significant performance degradation on novel or incomplete data.<n>These findings highlight the reliance on recall over rigorous logical inference.<n>This paper introduces a novel benchmark, termed as Math-RoB, that exploits hallucinations triggered by missing information to expose reasoning gaps.
  arXiv  Detail & Related papers  (2025-03-06T15:36:06Z)
• Preference Optimization for Reasoning with Pseudo Feedback [100.62603571434167]
  We introduce a novel approach to generate pseudo feedback for reasoning tasks by framing the labeling of solutions as an evaluation against associated test cases.<n>We conduct experiments on both mathematical reasoning and coding tasks using pseudo feedback for preference optimization, and observe improvements across both tasks.
  arXiv  Detail & Related papers  (2024-11-25T12:44:02Z)

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.