001 DeFiScreener: Efficient DeFi Attack Pre-screening in Smart Contracts via Historical Case Matching arXiv Paper Rui Cao, Shaojing Fan et al. 7 days ago 002 HarnessLLM: Rust Verification Harness Generation with Large Language Models arXiv Paper Minghua Wang, Yuwei Liu et al. 7 days ago 003 KaPilot: LLM-Assisted Generation of Kani Specifications for Unsafe Rust Verification arXiv Paper Minghua Wang, Yuxi Ling et al. 7 days ago 004 MineValiCoder: Reliable Code Generation with Test Case Quality Mining and Bipartite Graph-Based Mutual Validation arXiv Paper Zhenqian Zhao, Qihang Yang et al. 7 days ago 005 No Edges, No Verdict: A Large-Scale Empirical Study of Declared Dependency Graphs in 78K SBOMs in the Wild arXiv Paper Artur Zięba-Kozarzewski 7 days ago 006 No Snake Oil: Verifying Python Package Builds arXiv Paper Guoming Li, Jian Yang et al. 7 days ago 007 PoCEvolve: Generating Proof-of-Concept Exploits from Security Patches with Vulnerability-Aware Prompt Evolution arXiv Paper Duc Manh Tran, Ratnadira Widyasari et al. 7 days ago 008 Animation, Verification and Visualisation of Prolog Transition Systems with ProB arXiv Paper Jan Gruteser, Michael Leuschel et al. Jul 23 009 Anti-Goal Reasoning: Rethinking the Theory of Goal Reasoning in Non-Axiomatic Logic arXiv Paper Bowen Xu Jul 23 010 Bound-Founded Semantics for Answer Set Programming with Difference Constraints: Preliminary Report arXiv Paper Pedro Cabalar, Jorge Fandinno et al. Jul 23 011 Case study: proving sqrt(2) irrational with LPTP and an LLM arXiv Paper Fred Mesnard et al. Jul 23 012 Case study: solving P-99 with LPTP and an LLM arXiv Paper Fred Mesnard et al. Jul 23 013 Chess\_db: A framework for working with large chess game datasets arXiv Paper Nicos Angelopoulos, J. Wielemaker Jul 23 014 Declarative Problem Solving in UAM Strategic Deconfliction arXiv Paper Gioacchino Sterlicchio, A. Oddi et al. Jul 23 015 Delivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents arXiv Paper Swapnanil Saha Jul 23 016 Differentiable Logic Programming to Mitigate Reasoning Shortcuts in Neurosymbolic Systems arXiv Paper A. Takemura, Katsumi Inoue Jul 23 017 Encoding Event-B Proof Rules in Prolog: An Interactive Sequent Prover for ProB arXiv Paper Katharina Engels, Jan Gruteser et al. Jul 23 018 Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy arXiv Paper Vishnu Balachandran Jul 23 019 Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog arXiv Paper Bartolomeo Bogliolo Jul 23 020 Explainability Framework for Policy-Aware Autonomous Agents arXiv Paper Heather Merhout, Daniela Inclezan Jul 23 021 Explainable Belief Harmonization under Dynamic Epistemic Partitions arXiv Paper Adam Kostka, J. Chudziak Jul 23 022 From Resource Flow to Executable Tests: Petri-Net-Guided LLM Test Generation for Concurrent Stateful Rust APIs arXiv Paper Kaiwen Zhang, Guanjun Liu Jul 23 023 HiMe: Real-Time Self-Hosted Personal Agent Platform for Health Insights with Wearable Devices arXiv Paper Wei Liu, Siya Qi et al. Jul 23 024 How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests arXiv Paper Bertil Braun Jul 23 025 How Rules Represent Causal Knowledge: Causal Modeling with Probabilistic Logic Programming arXiv Paper Kilian Rueckschloss, Felix Weitkaemper Jul 23 026 Hybrid MKNF with Classical Negation in the Rule Component arXiv Paper A. Sheela, Christophe Rey et al. Jul 23 027 Logic Programming Semantics for Causal Processes arXiv Paper Felix Weitkämper Jul 23 028 Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and Images arXiv Paper Idris Karel Seunda Ekwe, Patrick Tenga Shako et al. Jul 23 029 Relaxed activation analysis of dataflow networks - A clock calculus for machine learning and real-time scheduling arXiv Paper William Gaudelier, Albert Cohen et al. Jul 23 030 Representative Sets in Propositional Abduction arXiv Paper J. Schmidt, Mohamed Maizia et al. Jul 23 031 Scaling Up Formal Representation of Clinical Trial Protocols in Ensemble Logic Using LLMs: A Preliminary Study arXiv Paper Yan Huang, Xubing Hao et al. Jul 23 032 Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction arXiv Paper Tencent WorkBuddy Bench Team Siqi Cai, Shaopeng Chen et al. Jul 23 033 Towards a Certifying Grounder arXiv Paper Daimy Van Caudenberg, Alexander Ek et al. Jul 23 034 Transformer-Assisted LLM-Based Source Code Summarisation: to Enable More Secure Software Development arXiv Paper Jesse Phillips, T. Hall et al. Jul 23 035 Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes arXiv Paper Yuhao Tan, Zhibang Yang et al. Jul 22 036 Don't Trust the Label: License Laundering in AI Supply Chains arXiv Paper James Jewitt, Hao Li et al. Jul 22 037 IssueTrojanBench: Benchmarking AI Coding Agents Against Malicious Issue Requests arXiv Paper Ankur Singh, Jinqiu Yang et al. Jul 22 038 Multi-stage Dynamic Selection for Cross-Project Defect Prediction arXiv Paper J. G. Avelino, J. S. A. Júnior et al. Jul 22 039 Operational Identity: A Finite Audit of Declared and Implemented Rules of Sameness arXiv Paper Denise M. Case Jul 22 040 PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization arXiv Paper Ryan Deng, Yuanzhe Liu et al. Jul 22 041 Security Vulnerability Patterns in AI-Generated Code: A Cross-Model Comparative Study arXiv Paper Shanna M. Kahn, John D. Hastings Jul 22 042 Test Case Prioritization for DNNs via Neural Collapse Instability arXiv Paper Chunyu Liu, Mingyuan Li et al. Jul 22 043 Graph-Based Agentic AI with LangGraph: Workflow Pathways for Long-Running Stateful Business Processes arXiv Paper Daniel Pearson, Sidney Shapiro et al. Jul 21 044 SciCodePile: A 128GB Corpus and Executable Benchmark for Challenging Scientific Code Generation arXiv Paper Weifeng Sun, Ye Fan et al. Jul 21 045 Skillware: A Software Ontology and Engineering Lifecycle for Persistent Behavioral Artifacts arXiv Paper Haodi Fan, Zucong Lan Jul 21 046 Spaghetti Architect: A Contamination-Resistant, By-Construction-Labelled, Multi-Language Code Dataset Generator arXiv Paper Yuxiang Ji Jul 21 047 Understanding Developer Pain Points in Federated Learning: Insights from Stack Overflow and GitHub arXiv Paper Sahand Saed, Khairul Alam et al. Jul 21 048 A Decision-Centered Reference Architecture for Trustworthy Agentic Commerce arXiv Paper Dimitrios S. Sfiris Jul 20 049 Autoresearch with Coding Agents: Generalizers and Metric-Maximizers on Quran Recitation Data arXiv Paper N. Askarbekuly, Mohamad Al Mdfaa et al. Jul 20 050 CODENS: Transforming Code Changes into Living, Accessible, and Queryable Documentation arXiv Paper Abdelhak Kelious, Chyrine Tahri et al. Jul 20 051 CommitLLM: A Fine-Tuned Pipeline for Git Commit Message Generation arXiv Paper Md Rafid Haque, P. Patel et al. Jul 20 052 Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments arXiv Paper Shuoming Zhang, Ruiyuan Xu et al. Jul 20 053 ETAS: An Effect-Typed Language for Agent Systems arXiv Paper Huiri Tan, Yikun Wang et al. Jul 20 054 FailureAtlas: A Taxonomy of Failure Modes in Multi-Provider LLM Serving Infrastructure arXiv Paper Vishal Pandey, Gopal Singh Jul 20 055 FlashPDE: A Drop-In Fused Triton Operator Library for Neural PDE Solvers arXiv Paper Peiyu Zang, Bosen Xie et al. Jul 20 056 Integrating High-Level Requirements to Low-Level Tests with Machine-Readable V&V Specifications arXiv Paper M. Arief, Nur Ahmad Khatim et al. Jul 20 057 Is Progressive Disclosure All You Need for Long-Context Agents? arXiv Paper Yifeng He, Yinzhe Zhao et al. Jul 20 058 Persona-as-Configuration: Generative Stakeholder Reporting for Agricultural Floods arXiv Paper Oliver Aleksander Larsen, Tiziano Santilli et al. Jul 20 059 SWE-Pruner Pro: The Coder LLM Already Knows What to Prune arXiv Paper Yuhang Wang, Yuling Shi et al. Jul 20 060 TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization arXiv Paper Alex Mathai, Shobini Iyer et al. Jul 20