Related papers: AkiraRust: Re-thinking LLM-aided Rust Repair Using a Feedback-guided Thinking Switch

AkiraRust: Re-thinking LLM-aided Rust Repair Using a Feedback-guided Thinking Switch

URL: http://arxiv.org/abs/2602.21681v1
Date: Wed, 25 Feb 2026 08:34:27 GMT
Title: AkiraRust: Re-thinking LLM-aided Rust Repair Using a Feedback-guided Thinking Switch
Authors: Renshuang Jiang, Yichong Wang, Pan Dong, Xiaoxiang Fang, Zhenling Duan, Tinglue Wang, Yuchen Hu, Jie Yu, Zhe Jiang,
Abstract summary: AkiraRust is a repair and verification framework that incorporates a finite-state machine to adapt its detection and repair flow to runtime semantic conditions.<n>AkiruRust achieves about 92% semantic correctness and delivers a 2.2x average speedup compared to SOTA.
Score: 25.65238229037917
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Eliminating undefined behaviors (UBs) in Rust programs requires a deep semantic understanding to enable accurate and reliable repair. While existing studies have demonstrated the potential of LLMs to support Rust code analysis and repair, most frameworks remain constrained by inflexible templates or lack grounding in executable semantics, resulting in limited contextual awareness and semantic incorrectness. Here, we present AkiraRust, an LLM-driven repair and verification framework that incorporates a finite-state machine to dynamically adapt its detection and repair flow to runtime semantic conditions. AkiraRust introduces a dual-mode reasoning strategy that coordinates fast and slow thinking across multiple agents. Each agent is mapped to an FSM state, and a waveform-driven transition controller manages state switching, rollback decisions, and semantic check pointing, enabling context-aware and runtime-adaptive repair. Experimental results show that AkiraRust achieves about 92% semantic correctness and delivers a 2.2x average speedup compared to SOTA.

Related papers

ForgeryVCR: Visual-Centric Reasoning via Efficient Forensic Tools in MLLMs for Image Forgery Detection and Localization [62.03035862528452]
ForgeryVCR is a framework that materializes imperceptible traces into explicit visual intermediates via Visual-Centric Reasoning.<n>ForgeryVCR achieves state-of-the-art (SOTA) performance in both detection and localization tasks.
arXiv Detail & Related papers (2026-02-15T11:14:47Z)
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)
VIGIL: A Reflective Runtime for Self-Healing Agents [0.0]
We present VIGIL, a reflective runtime that supervises a sibling agent and performs autonomous maintenance rather than task execution.<n> VIGIL ingests behavioral logs, appraises each event into a structured emotional representation, maintains a persistent EmoBank with decay and contextual policies, and derives an RBT diagnosis that sorts recent behavior into strengths, opportunities, and failures.
arXiv Detail & Related papers (2025-12-08T02:18:41Z)
SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation [65.6201974979119]
We propose SemanticVLA, a novel VLA framework that performs Semantic-Hierarchical Sparsification and Enhancement for Efficient Robotic Manipulation.<n>SemanticVLA surpasses OpenVLA on LIBERO benchmark by 21.1% in success rate, while reducing training cost and inference latency by 3.0-fold and 2.7-fold.
arXiv Detail & Related papers (2025-11-13T17:24:37Z)
InspectCoder: Dynamic Analysis-Enabled Self Repair through interactive LLM-Debugger Collaboration [71.18377595277018]
Large Language Models (LLMs) frequently generate buggy code with complex logic errors that are challenging to diagnose.<n>We present InspectCoder, the first agentic program repair system that empowers LLMs to actively conduct dynamic analysis via interactive debugger control.
arXiv Detail & Related papers (2025-10-21T06:26:29Z)
TrajBooster: Boosting Humanoid Whole-Body Manipulation via Trajectory-Centric Learning [79.59753528758361]
We present TrajBooster, a cross-embodiment framework that leverages abundant wheeled-humanoid data to boost bipedal VLA.<n>Our key idea is to use end-effector trajectories as a morphology-agnostic interface.<n>Results show that TrajBooster allows existing wheeled-humanoid data to efficiently strengthen bipedal humanoid VLA performance.
arXiv Detail & Related papers (2025-09-15T12:25:39Z)
Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent [6.300669721057781]
Meta-Policy Reflexion (MPR) is a framework that consolidates LLM-generated reflections into a structured, predicate-like Meta-Policy Memory (MPM)<n>MPR externalizes reusable corrective knowledge without model weight updates, enforces domain constraints to reduce unsafe or invalid actions, and retains the adaptability of language-based reflection.<n> Empirical results reported in the supplied material indicate consistent gains in execution accuracy and robustness when compared to Reflexion baselines; rule admissibility further improves stability.
arXiv Detail & Related papers (2025-09-04T08:18:39Z)
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)
Repeton: Structured Bug Repair with ReAct-Guided Patch-and-Test Cycles [1.387448620257867]
Large Language Models (LLMs) have shown strong capabilities in code generation and comprehension, yet their application to complex software engineering tasks often suffers from low precision and limited interpretability.<n>We present Repeton, a fully open-source framework that leverages LLMs for precise and automated code manipulation in real-world Git.
arXiv Detail & Related papers (2025-06-09T19:36:40Z)
Training Language Models to Generate Quality Code with Program Analysis Feedback [66.0854002147103]
Code generation with large language models (LLMs) is increasingly adopted in production but fails to ensure code quality.<n>We propose REAL, a reinforcement learning framework that incentivizes LLMs to generate production-quality code.
arXiv Detail & Related papers (2025-05-28T17:57:47Z)
Unlocking a New Rust Programming Experience: Fast and Slow Thinking with LLMs to Conquer Undefined Behaviors [9.305729184240272]
Rust introduces Undefined Behaviors (UBs) that reduce safety.<n>Eliminating these UBs requires a deep understanding of Rust's safety rules and strong typing.<n>We present a framework called RustBrain that automatically and flexibly minimizes UBs in Rust projects.
arXiv Detail & Related papers (2025-03-04T06:48:45Z)
ReF Decompile: Relabeling and Function Call Enhanced Decompile [50.86228893636785]
The goal of decompilation is to convert compiled low-level code (e.g., assembly code) back into high-level programming languages.<n>This task supports various reverse engineering applications, such as vulnerability identification, malware analysis, and legacy software migration.
arXiv Detail & Related papers (2025-02-17T12:38:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.