DocSync: Agentic Documentation Maintenance via Critic-Guided Reflexion

• URL: http://arxiv.org/abs/2605.02163v1
• Date: Mon, 04 May 2026 02:41:33 GMT
• Title: DocSync: Agentic Documentation Maintenance via Critic-Guided Reflexion
• Abstract summary: DocSync is an agentic workflow that frames documentation maintenance as a structurally grounded, iterative generation task.<n>We empirically evaluate a resource-constrained implementation of DocSync-using a LoRA-adapted small language model.<n>Our findings demonstrate that this AST-aware agentic approach substantially outperforms standard encoder-decoder baselines.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Software documentation frequently drifts from executable logic as codebases evolve, creating technical debt that degrades maintainability and causes downstream API misuse. While static analysis tools can detect the absence of documentation, they cannot evaluate its semantic consistency. Conversely, standard Large Language Models (LLMs) offer generative flexibility but frequently hallucinate when updating documentation without deep structural awareness of the underlying code. To address this gap, we propose DocSync, an agentic workflow that frames documentation maintenance as a structurally grounded, iterative generation task. DocSync bridges syntactic changes and natural language descriptions by fusing Abstract Syntax Tree (AST) representations and Retrieval-Augmented Generation (RAG) to provide dependency-aware context. Furthermore, to ensure factual consistency, we incorporate a critic-guided refinement loop based on the Reflexion paradigm, allowing the model to self-correct candidate updates against the source code. We empirically evaluate a resource-constrained implementation of DocSync-using a LoRA-adapted small language model - on a proxy code-to-text maintenance task. Our findings demonstrate that this AST-aware agentic approach substantially outperforms standard encoder-decoder baselines across semantic alignment, summary-line faithfulness, and automated judge preferences (e.g., achieving an automated judge score of 3.44/5.0 compared to 1.91 for CodeT5-base). Crucially, the iterative critic loop yields measurable improvements in semantic correctness without requiring scaled-up parameter counts. These results provide strong evidence that coupling structural retrieval with agentic refinement is a highly promising direction for autonomously mitigating documentation debt.

Related papers

• RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists [12.810164698494281]
  RepoProbe is a novel benchmark for evaluating repository-level code understanding.<n>We propose a Checklist-Based Verification Protocol that decomposes answers into atomic, verifiable facts.
  arXiv  Detail & Related papers  (2026-08-05T12:49:36Z)
• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph Retrieval [25.28453025760491]
  We introduce LEDGER to tackle the novel context engineering challenge of agentic document editing.<n>LEDGER constructs a lightweight dependency graph that explicitly models document structure.<n>We evaluate LEDGER on a benchmark of 1.9k test cases with various document types and lengths.
  arXiv  Detail & Related papers  (2026-06-19T17:35:05Z)
• Automating Formal Verification with Agent-Guided Tree Search [0.0]
  Formal verification offers a path to provably correct software, but writing verified code remains expensive enough that the technique is rarely used in production.<n>Recent benchmarks measure their ability to translate specifications into code and machine-checked iteration of correctness.<n>This thesis evaluates the state of such LLM-driven verified-code generation in Lean and develops search-based methods for improving performance.
  arXiv  Detail & Related papers  (2026-05-26T14:50:47Z)
• FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation [73.22935457705057]
  We introduce FRESCO, a benchmark for evaluating re-rankers in temporally dynamic contexts.<n>By pairing recency-seeking queries with historical Wikipedia revisions, FRESCO tests whether re-rankers can prioritize factually recent evidence while maintaining semantic relevance.<n>Our evaluation reveals a consistent failure mode across existing re-rankers: a strong bias toward older, semantically rich documents, even when they are factually obsolete.
  arXiv  Detail & Related papers  (2026-04-14T17:04:25Z)
• ReqToCode: Embedding Requirements Traceability as a Structural Property of the Codebase [0.0]
  This paper introduces ReqToCode, an approach that prevents trace degradation by embedding traceable system elements directly into the system.<n>We describe the approach, its architectural principles, the Traceable lifecycle, and illustrate it with a generic example spanning requirement definition, artifact generation, code integration, and build-time validation.
  arXiv  Detail & Related papers  (2026-03-14T16:00:09Z)
• DiffuRank: Effective Document Reranking with Diffusion Language Models [71.16830004674513]
  We propose DiffuRank, a reranking framework built upon diffusion language models (dLLMs)<n>dLLMs support more flexible decoding and generation processes that are not constrained to a left-to-right order.<n>We show dLLMs achieve performance comparable to, and in some cases exceeding, that of autoregressive LLMs with similar model sizes.
  arXiv  Detail & Related papers  (2026-02-13T02:18:14Z)
• Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation [17.125957722393327]
  Stream of Revision is a paradigm shift that elevates code generation from a monotonic stream to a dynamic, self-correcting trajectory.<n>We introduce specific action tokens that enable the model to seamlessly backtrack and edit its own history within a single forward pass.
  arXiv  Detail & Related papers  (2026-02-01T12:22:46Z)
• Veri-Sure: A Contract-Aware Multi-Agent Framework with Temporal Tracing and Formal Verification for Correct RTL Code Generation [4.723302382132762]
  silicon-grade correctness remains bottlenecked by: (i) limited test coverage and reliability of simulation-centric evaluation, (ii) regressions and repair hallucinations, and (iii) semantic drift as intent is reinterpreted across agent handoffs.<n>We propose Veri-Sure, a multi-agent framework that establishes a design contract to align agents' intent and uses a patching mechanism guided by static dependency slicing to perform precise, localized repairs.
  arXiv  Detail & Related papers  (2026-01-27T16:10:23Z)
• DiffuGR: Generative Document Retrieval with Diffusion Language Models [80.78126312115087]
  We propose generative document retrieval with diffusion language models, dubbed DiffuGR.<n>For inference, DiffuGR attempts to generate DocID tokens in parallel and refine them through a controllable number of denoising steps.<n>In contrast to conventional left-to-right auto-regressive decoding, DiffuGR provides a novel mechanism to first generate more confident DocID tokens.
  arXiv  Detail & Related papers  (2025-11-11T12:00:09Z)
• Cognitive-Aligned Document Selection for Retrieval-augmented Generation [2.9060210098040855]
  We propose GGatrieval to dynamically update queries and filter high-quality, reliable retrieval documents.<n>We parse the user query into its syntactic components and perform fine-grained grounded alignment with the retrieved documents.<n>Our approach introduces a novel criterion for filtering retrieved documents, closely emulating human strategies for acquiring targeted information.
  arXiv  Detail & Related papers  (2025-02-17T13:00:15Z)
• COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
  Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
  arXiv  Detail & Related papers  (2024-10-12T23:56:19Z)
• Autoregressive Search Engines: Generating Substrings as Document Identifiers [53.0729058170278]
  Autoregressive language models are emerging as the de-facto standard for generating answers. Previous work has explored ways to partition the search space into hierarchical structures. In this work we propose an alternative that doesn't force any structure in the search space: using all ngrams in a passage as its possible identifiers.
  arXiv  Detail & Related papers  (2022-04-22T10:45:01Z)
• GERE: Generative Evidence Retrieval for Fact Verification [57.78768817972026]
  We propose GERE, the first system that retrieves evidences in a generative fashion. The experimental results on the FEVER dataset show that GERE achieves significant improvements over the state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-04-12T03:49:35Z)

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.