error recovery strategies

This work addresses the high false-positive rate and insufficient precision and automation in program bug detection. We propose a bidirectional collaborative analysis framework integrating Incorrectness Logic (IL) and Sufficient Incorrectness Logic (SIL). Our approach introduces a rule-level guidance mechanism that dynamically steers subsequent reasoning using prior analysis results, coupled with path pruning, loop unrolling, and dynamic instrumentation of proof rules to enable cross-logic information reuse. The method significantly improves joint accuracy in error reachability verification and fault-triggering input reconstruction while preserving scalability and enhancing industrial applicability. Experimental evaluation demonstrates substantial improvements over single-logic approaches in three key dimensions: (i) bug localization accuracy, (ii) causal explainability of defects, and (iii) efficiency of automated analysis. Our framework establishes a novel paradigm for scalable, automated code contract generation.

Automatically generating high-quality, correct, and complete formal specifications—such as those in JML—remains a significant challenge: existing approaches often produce specifications that pass syntactic validation yet suffer from semantic inaccuracies or insufficient coverage. This work proposes VeriAct, a novel framework that introduces Spec-Harness, the first evaluation mechanism capable of precisely assessing both correctness and completeness of generated specifications. VeriAct further establishes the first verification-guided agent system, leveraging large language models within a closed-loop iterative process that integrates code execution, formal verification, and feedback signals to collaboratively synthesize and repair specifications. Experimental results demonstrate that VeriAct substantially outperforms current methods on two benchmarks, yielding specifications that not only satisfy verifiers but also achieve higher standards of semantic correctness and completeness.

This work addresses the challenge that program specifications generated from natural language are often too weak or overly restrictive for effective verification, and existing approaches are constrained by a single verification paradigm, struggling to balance automation with expressiveness. The paper proposes Velvet, a multimodal verifier architecture that unifies dynamic testing, automated reasoning, and interactive proving within a certified program synthesis pipeline, enabling specification validation, task decomposition, and proof delegation. Built upon Lean, Velvet integrates random property-based testing, verification-condition-guided divide-and-conquer synthesis, and state-of-the-art AI-powered theorem provers. Experiments demonstrate that the approach effectively uncovers flaws in existing specifications on standard benchmarks, substantially increases the rate of fully verified solutions, and maintains consistent performance across different large language model backends.

Existing program verification approaches struggle to reliably identify skill deficiencies and extract actionable improvement signals from ambiguous feedback. This work proposes the first skill self-evolution framework tailored for program verification, which attributes verification failures to specific skill gaps, extracts diagnostic features as reusable experience, and selectively adopts only those skill revisions that enhance verification performance while preserving program semantics. Integrating large language model agents, verification trajectory analysis, diagnostic signature extraction, and an iterative optimization mechanism under semantic constraints, the framework consistently outperforms current baselines across diverse verification tools, agent architectures, and large model backends, thereby overcoming the limitations of traditional self-evolution methods in complex verification scenarios.

This work addresses the insufficient correctness guarantees in program synthesis by proposing a collaborative synthesis framework integrating dynamic multi-agent workflows with an LLM-based quality checker. Methodologically, it establishes a closed-loop collaboration among code generation, test execution, and self-debugging agents, and introduces the first LLM quality checker that explicitly models program execution traces to assess test compliance in real time—enabling dynamic submission, issue clarification, and step-level backtracking—augmented by diverse prompting and quality-feedback-driven adaptive decision-making. The key contribution is the first integration of dynamic execution-aware quality verification into the synthesis pipeline, enabling fine-grained procedural control. Empirically, the approach achieves state-of-the-art performance on MBPP, HumanEval, and EvalPlus, significantly outperforming static workflows and zero-shot one-shot synthesis baselines.

This work addresses the prevalent issue in autonomous coding agents that prematurely declare lifecycle states—such as “DONE”—without verification during multi-step software tasks, often leading to erroneous progression. To mitigate this, the authors propose Proof-or-Stop, a model-agnostic and platform-neutral trusted control layer that strictly gates state transitions only when fresh, traceable, and mechanically verifiable evidence satisfies predefined conditions. Crucially, the approach treats agent outputs as claims pending validation rather than established facts, and explicitly distinguishes between the mere existence of review mechanisms and their role as gating criteria. Empirical evaluation demonstrates zero false “DONE” declarations across ten scenarios, successful resistance against 18 classes of tampering attacks with no false acceptances, and a reduction in hidden failure rates from 31/1800 to 2/1800 in ablation studies. Furthermore, 94.8% of issues in a corpus of 565 self-application narratives were resolved.

This work addresses the high false positive rate of large language models (LLMs) in detecting concurrency bugs, which often wastes developer effort. To mitigate this, the authors propose Mizzle—the first complete incorrectness separation logic tailored to a concurrent subset of OCaml—that mandates every LLM-generated bug report be accompanied by a machine-checkable proof certifying the error’s actual reachability. Mechanized in the Rocq proof assistant using the Iris framework, Mizzle supports multiple error semantics, including deadlocks, non-linearizability, and race conditions, and comes with rigorous formal guarantees of soundness (no false positives) and completeness (all genuine errors are provable). A case study demonstrates that LLMs can effectively leverage this logic to produce verifiable bug reports.

This work addresses a critical structural vulnerability in large language model (LLM)-based AI agents during multi-turn interactions, where flawed planning modules can lead to safety intent degradation and erroneous state perception, resulting in constraint violations or execution deadlocks. The study systematically characterizes this issue for the first time and introduces a lightweight architectural layer that integrates intent-action consistency verification, runtime state tracking, and a forced termination mechanism to provide non-intrusive reliability guarantees. Through rigorous experiments in high-risk multi-turn scenarios and a controlled evaluation framework—augmented with a declaration-action gap metric and an action-aware supervision layer—the proposed approach effectively intercepts policy violations across multiple mainstream LLMs while minimizing false positives, thereby significantly enhancing the long-term safety and stability of autonomous agent execution.

Program verification is inherently undecidable, and existing tools either lack sufficient user interaction capabilities or operate at an abstraction level too low to enable users to effectively comprehend proof states and correct errors. This work proposes a novel interactive verification approach that, for the first time, enables direct visualization of and intervention in proof states at the source code and specification levels, thereby bridging the cognitive gap between high-level semantics and low-level logical reasoning. A prototype system built upon the Java verification engine KeY integrates automated and interactive techniques to allow users to guide proof exploration at a high semantic level. User studies demonstrate that this method significantly enhances users’ understanding of the verification process and enables more efficient identification of flaws in either code or specifications.

This work addresses the challenge of formal verification for Reflex programs in industrial-scale control systems, where the generation of an excessive number of verification conditions often renders manual analysis impractical. To overcome this limitation, the authors propose a hybrid verification strategy that integrates a structured requirement annotation language with automated invariant inference based on program structure, coupled with an SMT solver to automatically discharge a substantial subset of verification conditions. By leveraging this synergistic approach, the method significantly reduces the number of verification tasks requiring human intervention, thereby enhancing the automation, feasibility, and overall efficiency of formal verification for large-scale process control systems.