{"total":65,"rows":[{"id":"2412.20367","title":"Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Survey","created":"2024-12-29","cited_by_count":83,"area":null},{"id":"2506.08837","title":"Design Patterns for Securing LLM Agents against Prompt Injections","created":"2025-06-10","cited_by_count":73,"area":"agents"},{"id":"2601.17548","title":"Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems","created":"2026-01-24","cited_by_count":31,"area":"agents"},{"id":"2603.11088","title":"The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey","created":"2026-03-11","cited_by_count":28,"area":"agents"},{"id":"2509.07764","title":"AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents","created":"2025-09-09","cited_by_count":27,"area":"agents"},{"id":"2501.18617","title":"DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs","created":"2025-01-24","cited_by_count":20,"area":"lr"},{"id":"2604.06550","title":"SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills","created":"2026-04-08","cited_by_count":20,"area":"agents"},{"id":"2504.20799","title":"Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges","created":"2025-04-29","cited_by_count":11,"area":null},{"id":"2505.23657","title":"Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation","created":"2025-05-29","cited_by_count":10,"area":null},{"id":"2602.19555","title":"SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime","created":"2026-02-23","cited_by_count":8,"area":"agents"},{"id":"2512.21577","title":"A Unified Definition of Hallucination: It's The World Model, Stupid!","created":"2025-12-25","cited_by_count":6,"area":"wm"},{"id":"2606.05391","title":"Human oversight of agentic systems in practice: Examining the oversight work, challenges, and heuristics of developers using software agents","created":"2026-06-03","cited_by_count":6,"area":"agents"},{"id":"2410.14748","title":"ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries","created":"2024-10-17","cited_by_count":5,"area":null},{"id":"2605.09594","title":"Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills","created":"2026-05-10","cited_by_count":5,"area":"agents"},{"id":"2510.11195","title":"RAG-Pull: Turning Retrieval into a Code-Injection Channel via Invisible Unicode Perturbations","created":"2025-10-13","cited_by_count":4,"area":"rag"},{"id":"2605.30777","title":"What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2511.08877","title":"Hierarchical Memorization in Large Language Models: Evidence from Citation Generation","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2512.21250","title":"CoTDeceptor:Adversarial Code Obfuscation Against CoT-Enhanced LLM Code Agents","created":"2025-12-24","cited_by_count":3,"area":"agents"},{"id":"2603.18740","title":"Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Review","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2409.15228","title":"A Comprehensive Framework for Evaluating API-oriented Code Generation in Large Language Models","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2508.05693","title":"Empirical Evaluation of AI-Assisted Software Package Selection: A Knowledge Graph Approach","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2510.25378","title":"Hallucinations in Bibliographic Recommendation: Citation Frequency as a Proxy for Training Data Redundancy","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2410.06462","title":"Hallucinating AI Hijacking Attack: Large Language Models and Malicious Code Recommenders","created":"2024-10-09","cited_by_count":1,"area":"safety"},{"id":"2505.02144","title":"VECSR: Virtually Embodied Common Sense Reasoning System","created":"2025-05-04","cited_by_count":1,"area":"lr"},{"id":"2509.20277","title":"Investigating Security Implications of Automatically Generated Code on the Software Supply Chain","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2509.22202","title":"Library Hallucinations in LLM-Generated Code: A Risk Analysis Grounded in Developer Queries","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2509.23835","title":"HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2510.05342","title":"Margin Adaptive DPO: Leveraging Reward Model for Granular Control in Preference Optimization","created":"2025-10-06","cited_by_count":1,"area":"alignment"},{"id":"2510.09633","title":"Hound: Relation-First Knowledge Graphs for Complex-System Reasoning in Security Audits","created":"2025-09-29","cited_by_count":1,"area":"lr"},{"id":"2511.05626","title":"LLMs as Packagers of HPC Software","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2512.11984","title":"Evidence-Driven Decision Support for AI Model Selection in Research Software Engineering","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2603.15351","title":"PMAx: An Agentic Framework for AI-Driven Process Mining","created":"2026-03-16","cited_by_count":1,"area":"agents"},{"id":"2605.06279","title":"Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.14478","title":"When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context","created":"2026-05-14","cited_by_count":1,"area":"rag"},{"id":"2605.29354","title":"Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills","created":"2026-05-28","cited_by_count":1,"area":"agents"},{"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":"2607.00738","title":"Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2607.25076","title":"Towards an Agent Operating System - Lessons from Classical and Cloud OS","created":"2026-07-27","cited_by_count":1,"area":"agents"},{"id":"2609.02774","title":"CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation","created":"2026-09-02","cited_by_count":1,"area":"rag"},{"id":"2609.13437","title":"LabAgent: Customize Any Research Hubs for Scientific Discoveries Using AI Agents","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2408.01877","title":"Improving Zero-Shot ObjectNav with Generative Communication","created":"2024-08-03","cited_by_count":0,"area":null},{"id":"2508.20119","title":"LLM Agents for Generating Microservice-based Applications: how complex is your specification?","created":"2025-08-22","cited_by_count":0,"area":"agents"},{"id":"2604.07755","title":"An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.16377","title":"GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2605.01047","title":"LLM Ghostbusters: Surgical Package Hallucination Suppression via Adaptive Unlearning","created":"2026-05-01","cited_by_count":0,"area":"safety"},{"id":"2605.13115","title":"DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense","created":"2026-05-13","cited_by_count":0,"area":"diffusion"},{"id":"2605.17062","title":"The Range Shrinks, the Threat Remains: Re-evaluating LLM Package Hallucinations on the 2026 Frontier-Model Cohort","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.21405","title":"Stdlib or Third-Party? Empirical Performance and Correctness of LLM-Assisted Zero-Dependency Python Libraries","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.15283","title":"AI-driven Software Development: A Pragmatic Path to Agentic Development Processes","created":"2026-06-13","cited_by_count":0,"area":"agents"},{"id":"2606.25402","title":"LibEvoBench: Probing Temporal Knowledge Stratification in Code Generation Models","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.07433","title":"Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks via Universal and Transferable Adversarial HalluSquatting","created":"2026-07-08","cited_by_count":0,"area":"agents"},{"id":"2607.08981","title":"The Patchwork Problem in LLM-Generated Code","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.12340","title":"Skills That Don't Exist: A Large-Scale Study of Hallucinated Skill Recommendation in LLM Agents","created":"2026-07-14","cited_by_count":0,"area":"agents"},{"id":"2607.16660","title":"From Adoption to Deployment: A Qualitative Study on AI Integration in Software Development Practice","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2607.18357","title":"Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragments","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.00143","title":"Symbolic Attack Chain Generation from Atomic Red Team Techniques: An Empirical Study of Predicate Representation Granularity","created":"2026-07-31","cited_by_count":0,"area":"safety"},{"id":"2608.22652","title":"Evaluating Inference-Time Defenses Against Package Hallucination in LLM-Generated Code","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.07754","title":"Do AI Coding Assistants Check Before They Install? A Pre-Registered Demand-Side Audit of Trust Signals in the Research Software Supply Chain","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.12039","title":"Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering","created":"2026-09-10","cited_by_count":0,"area":"agents"},{"id":"2609.35889","title":"SINGED: Correct Outputs Do Not Certify Safe Execution in LLM Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2610.01768","title":"The Innocent Courier: Covert Exfiltration Through Legitimate LLM Web Fetching","created":"2026-10-01","cited_by_count":0,"area":"safety"},{"id":"2610.02456","title":"SideKernel: A Usable microVM Sandbox for AI Coding Agents on macOS","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.03857","title":"Beware EviLLM: Enabling Vulnerability Injection via Large Language Models","created":"2026-10-02","cited_by_count":0,"area":"safety"},{"id":"2610.13626","title":"SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14968","title":"SEEK: Agentic Knowledge Graph Retrieval for Secure Code Generation","created":"2026-10-10","cited_by_count":0,"area":"agents"}],"next_cursor":null}