Self-Improving AI Coding Agents Through Accumulated Behavioral Rules: A Closed-Loop Framework

• URL: http://arxiv.org/abs/2607.13091v1
• Date: Mon, 13 Jul 2026 21:13:46 GMT
• Title: Self-Improving AI Coding Agents Through Accumulated Behavioral Rules: A Closed-Loop Framework
• Abstract summary: We present a closed-loop framework in which every accepted review comment is codified as a persistent behavioral rule.<n>The framework combines an accumulating rule set in a version-controlled instruction file, a self-review checklist, and automated validation.<n>We show that our framework achieves persistent cross-session learning without weight updates, operates on productions rather than synthetic benchmarks, and addresses an experiential dimension (behavioral consistency over time) that existing benchmarks do not measure.
• Score: 0.3867363075280543
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM-based coding agents repeat the same classes of mistakes across sessions because they lack a mechanism to retain corrections from human review feedback. We present a closed-loop framework in which every accepted review comment is codified as a persistent behavioral rule, progressively expanding the set of error classes the agent can self-detect. The framework combines an accumulating rule set in a version-controlled instruction file, a self-review checklist executed before code submission, and automated validation that ensures rule set integrity as it grows. In deployment across a 35+ service microservices platform, the rule set grew from 5 to 18 behavioral rules, 15+ language-specific standards, and a 15-item self-review checklist, all derived from real review feedback. We present empirical results from 11 recorded working sessions spanning code generation, PR review, incident investigation, and cross service refactoring. We observe that accumulated rules shift review effort from low-level correctness toward design-level validation, achieve a measured 0% recurrence rate for ruled-against error classes, and transfer across heterogeneous agent interfaces. We compare our approach against related work in experiential LLM learning (Reflexion, ExpeL, Voyager) and automated code review (CodeReviewer, SWE-bench agents), showing that our framework achieves persistent cross-session learning without weight updates, operates on production codebases rather than synthetic benchmarks, and addresses an orthogonal dimension (behavioral consistency over time) that existing benchmarks do not measure. The result is a coding agent that improves with every review cycle, accumulating the engineering wisdom of its human collaborators without changing a single model weight.

Related papers

• MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic Coding [83.0805548642958]
  MTAC-IFBench is a comprehensive benchmark for instruction-following in software development.<n>It features multi-turn progressive software development instructions with diverse constraints spanning 6 primary and 18 secondary categories.<n>MTAC-IFBench identifies significant deficiencies in existing code agents in multi-turn instruction-following, with their performance degrading rapidly as the interaction session grows longer.
  arXiv  Detail & Related papers  (2026-09-14T03:57:37Z)
• MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves [65.60481414910728]
  Recursive self-improvement lets a system improve the model-building machinery from its own failures, so every later model inherits the gain.<n>Yet RSI has been validated almost exclusively on coding and formal benchmarks such as science QA and mathematics.<n>We argue RSI must next operate across real, diverse scientific, engineering, and meta-scientific domains, not where formal evaluation is merely tractable.<n>We present MetaRSI-v1, where improvement is the scheduled composition of three typed operators over one unified paradigm.
  arXiv  Detail & Related papers  (2026-09-06T05:15:31Z)
• Verification-Aware Training for Speculative Decoding [57.84976863792784]
  We introduce Verification-Aware Training (VAT), a plug-in framework that simulates verification at every training step and turns the resulting accept and reject patterns into supervision.<n>VAT modifies only the training objective, so it can be layered on top of existing methods without changing the draft architecture, the target model, or the inference procedure.<n>VAT improves average acceptance length by up to 11.4% and wall-clock speedup by up to 8.7%, with consistent gains across math, code, and chat benchmarks.
  arXiv  Detail & Related papers  (2026-08-31T01:42:10Z)
• AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows [1.6785141970297952]
  AEVAL (Agentic Evaluation) is a CI-integrated framework that replaces this practice with a deterministic, reproducible test pipeline for agentic skills.<n>Every skill change triggers a test event: the skill runs against a developer declared evaluation contract inside an automated executor.<n>A key ingredient is a structural separation between executor and grader, preventing a subtle but pervasive failure mode.
  arXiv  Detail & Related papers  (2026-07-16T21:33:05Z)
• TTHE: Test-Time Harness Evolution [50.26245555541721]
  Existing approaches optimize such harnesses before deployment, searching training or development data for a fixed agent workflow that is then frozen at test time.<n>We ask whether the harness can instead be optimized during evaluation itself, using only the unlabeled execution traces the agent produces on the test inputs.<n>During evaluation, TTHE maintains a population of candidate harnesses and refines them through an agentic proposer that reasons over their execution traces.<n>A judge then commits an improved harness from execution-derived proxy signals, and the selected program persists to govern subsequent inputs.
  arXiv  Detail & Related papers  (2026-07-09T05:53:39Z)
• SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review [47.72392142544407]
  Coding agents increasingly generate pull requests (PRs) for real-world software issues.<n>One-shot PR generation remains open-loop: the PR is proposed without systematic review, diagnosis, or revision.<n>We introduce textbfSWE-Review, a framework for closing this loop with agentic code review.
  arXiv  Detail & Related papers  (2026-07-07T09:37:45Z)
• Benchmarking Code Improvement with Progressive, Adaptive, and Interactive Feedback [13.976149104483449]
  PAIR-Bench is a progressive benchmark for evaluating large language models (LLMs)<n>It transforms an incorrect or incomplete program into a more correct one through feedback-guided refinement.<n>It measures whether a model repairs targeted failures, generalizes beyond the hint, preserves already-correct behavior, and how much assistance it requires.
  arXiv  Detail & Related papers  (2026-07-01T18:20:27Z)
• RAG-Reflect: Agentic Retrieval-Augmented Generation with Reflections for Comment-Driven Code Maintenance on Stack Overflow [0.5607590231264274]
  This paper demonstrates how agentic AI principles can revolutionize software maintenance tasks by presenting RAG-Reflect.<n>RAG-Reflect is a modular framework that achieves fine-tuned-level performance for valid comment-edit prediction without task-specific training.<n>We evaluate RAG-Reflect on the publicly available SOUP benchmark, achieving Precision = 0.81, Recall = 0.74, and F1 = 0.78.
  arXiv  Detail & Related papers  (2026-04-24T04:49:58Z)
• Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints [17.818522356206977]
  Most large language model (LLM)-based repair systems treat behavioral constraints as fixed during repair.<n>We propose Agent-CoEvo, a coevolutionary multi-agent framework in which candidate code patches and test patches are jointly explored and refined.<n>Agent-CoEvo consistently outperforms state-of-the-art agent-based and agentless baselines in both repair success and test reproduction quality.
  arXiv  Detail & Related papers  (2026-04-06T10:26:46Z)
• An Agentic Evaluation Framework for AI-Generated Scientific Code in PETSc [7.236134946837382]
  petscagent-bench is an agentic framework built on an agents-evaluating-agents paradigm.<n>It orchestrates a 14-evaluator pipeline across five scoring categories: correctness, performance, code quality, algorithmic appropriateness, and library-specific conventions.<n>We demonstrate the framework on a benchmark suite of realistic problems using the PETSc library for HPC.
  arXiv  Detail & Related papers  (2026-03-16T22:46:10Z)
• Can LLMs Compress (and Decompress)? Evaluating Code Understanding and Execution via Invertibility [36.41073880422337]
  We present RoundTripCodeEval (RTCE), a comprehensive benchmark consisting of four distinct code execution reasoning tasks.<n>We systematically evaluate state-of-the-art Code-LLMs using zero-shot prompting, supervised fine-tuning on execution traces, and self-reflection mechanisms.<n>RTCE surfaces several new and previously unmeasured insights that are not captured by existing I/O-prediction, execution-reasoning, or round-trip natural-language benchmarks.
  arXiv  Detail & Related papers  (2026-01-19T21:09:48Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• Sifting through the Chaff: On Utilizing Execution Feedback for Ranking the Generated Code Candidates [46.74037090843497]
  Large Language Models (LLMs) are transforming the way developers approach programming by automatically generating code based on natural language descriptions. This paper puts forward RankEF, an innovative approach for code ranking that leverages execution feedback. Experiments on three code generation benchmarks demonstrate that RankEF significantly outperforms the state-of-the-art CodeRanker.
  arXiv  Detail & Related papers  (2024-08-26T01:48:57Z)
• Deep Just-In-Time Inconsistency Detection Between Comments and Source Code [51.00904399653609]
  In this paper, we aim to detect whether a comment becomes inconsistent as a result of changes to the corresponding body of code. We develop a deep-learning approach that learns to correlate a comment with code changes. We show the usefulness of our approach by combining it with a comment update model to build a more comprehensive automatic comment maintenance system.
  arXiv  Detail & Related papers  (2020-10-04T16:49:28Z)

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.