{"total":53,"rows":[{"id":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178,"area":"agents"},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86,"area":"agents"},{"id":"2408.02232","title":"SpecRover: Code Intent Extraction via LLMs","created":"2024-08-05","cited_by_count":72,"area":"agents"},{"id":"2505.23135","title":"VERINA: Benchmarking Verifiable Code Generation","created":"2025-05-29","cited_by_count":34,"area":null},{"id":"2410.15756","title":"Automated Proof Generation for Rust Code via Self-Evolution","created":"2024-10-21","cited_by_count":33,"area":null},{"id":"2505.23486","title":"Autoformalization in the Era of Large Language Models: A Survey","created":"2025-05-29","cited_by_count":21,"area":null},{"id":"2412.06512","title":"The Fusion of Large Language Models and Formal Methods for Trustworthy AI Agents: A Roadmap","created":"2024-12-09","cited_by_count":20,"area":"agents"},{"id":"2502.18917","title":"ClassInvGen: Class Invariant Synthesis using Large Language Models","created":"2025-02-26","cited_by_count":11,"area":null},{"id":"2601.09822","title":"LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities","created":"2026-01-14","cited_by_count":8,"area":"agents"},{"id":"2512.23511","title":"Beyond Correctness: Exposing LLM-generated Logical Flaws in Reasoning via Multi-step Automated Theorem Proving","created":"2025-12-29","cited_by_count":6,"area":"lr"},{"id":"2605.25232","title":"Specification-Based Code-Text-Code Reengineering for LLM-Mediated Software Evolution","created":"2026-05-24","cited_by_count":5,"area":null},{"id":"2504.15284","title":"EditLord: Learning Code Transformation Rules for Code Editing","created":"2025-03-10","cited_by_count":4,"area":null},{"id":"2508.18675","title":"Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision","created":"2025-08-26","cited_by_count":4,"area":"agents"},{"id":"2602.11136","title":"FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight","created":"2026-02-11","cited_by_count":4,"area":"agents"},{"id":"2604.12268","title":"CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2509.24515","title":"Agentic Specification Generator for Move Programs","created":"2025-09-29","cited_by_count":3,"area":"agents"},{"id":"2404.09384","title":"Generative transformations and patterns in LLM-native approaches for software verification and falsification","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2502.15217","title":"FormalSpecCpp: A Dataset of C++ Formal Specifications created using LLMs","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2506.10704","title":"Formalising Software Requirements using Large Language Models","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2509.23130","title":"SysMoBench: Evaluating AI on Formally Modeling Complex Real-World Systems","created":"2025-09-27","cited_by_count":2,"area":null},{"id":"2509.23686","title":"Evaluating Program Semantics Reasoning with Type Inference in System F","created":"2025-09-28","cited_by_count":2,"area":"lr"},{"id":"2509.25043","title":"Large Language Models for Software Testing: A Research Roadmap","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2602.04892","title":"Doc2Spec: Synthesizing Formal Programming Specifications from Natural Language via Grammar Induction","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2604.00280","title":"Spec-Harness: Assessing and Guiding LLM-Synthesized Formal Specifications Beyond Verifiability","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2604.10392","title":"Intent-aligned Formal Specification Synthesis via Traceable Refinement","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2503.13279","title":"Goal2Story: A Multi-Agent Fleet based on Privately Enabled sLLMs for Impacting Mapping on Requirements Elicitation","created":"2025-03-17","cited_by_count":1,"area":"agents"},{"id":"2509.06239","title":"Proof2Silicon: Prompt Repair for Verified Code and Hardware Generation via Reinforcement Learning","created":"2025-09-07","cited_by_count":1,"area":"lr"},{"id":"2510.17163","title":"TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2602.12058","title":"ModelWisdom: An Integrated Toolkit for TLA+ Model Visualization, Digest and Repair","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2603.03668","title":"Can LLM Aid in Solving Constraints with Inductive Definitions?","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2606.05792","title":"Can LLMs Write Correct TLA+ Specifications? Evaluating Natural-Language-to-TLA+ Generation","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.17637","title":"Brick-DICL: Dynamic In-Context Learning for Automated Brick Schema Classification","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2607.13303","title":"Faithful Autoformalization of Natural Language Assertions","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2506.14627","title":"Working Document -- Formalising Software Requirements with Large Language Models","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2508.16071","title":"From Benchmark Data To Applicable Program Repair: An Experience Report","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2512.15816","title":"A Neurosymbolic Approach to Loop Invariant Generation via Weakest Precondition Reasoning","created":"2025-12-17","cited_by_count":0,"area":"lr"},{"id":"2604.15359","title":"AutoFlows++: Hierarchical Message Flow Mining for System on Chip Designs","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2605.01394","title":"LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation","created":"2026-05-02","cited_by_count":0,"area":"agents"},{"id":"2605.11315","title":"Natural Language based Specification and Verification","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.23931","title":"BODHI: Precise OS Kernel Specification Inference","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.27531","title":"Agentic Separation Logic Specification Synthesis","created":"2026-05-26","cited_by_count":0,"area":"agents"},{"id":"2606.18619","title":"Code-Augur: Agentic Vulnerability Detection via Specification Inference","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2606.19588","title":"Analyzing the Narration Gap in LLM-Solver Loops","created":"2026-06-17","cited_by_count":0,"area":"lr"},{"id":"2606.20969","title":"AutoACSL: Synthesizing ACSL Specifications by Integrating LLMs with CPG-Based Static Analysis","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.09366","title":"Diversifying to Verify: When Task-Equivalent Programs Differ in Verifiability","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.22902","title":"How Well Can AI Generate Backlogs from App Mockups?","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.25333","title":"Specula: Scaling formal specifications for autonomous model checking of system code","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.06052","title":"SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.25018","title":"OSFoundry: Building and Evolving Operating Systems with Specification-Guided Agents","created":"2026-08-08","cited_by_count":0,"area":"agents"},{"id":"2609.39022","title":"From Verification Failures to Reusable Guidance for Coding Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.39568","title":"Self-Spec Verifiable Code Generation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.16870","title":"SpecGuardBench: Can Coding Agents Construct Reliable Validation Harnesses from Natural Language Specifications?","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17358","title":"claimcheck: Measuring and Improving Specification Faithfulness","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}