{"total":59,"rows":[{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"area":null},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2510.04550","title":"TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use","created":"2025-10-06","cited_by_count":51,"area":"agents"},{"id":"2505.16944","title":"AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios","created":"2025-05-22","cited_by_count":49,"area":"agents"},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2505.16120","title":"LLM-Powered AI Agent Systems and Their Applications in Industry","created":"2025-05-22","cited_by_count":22,"area":"agents"},{"id":"2508.18298","title":"Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms","created":"2025-08-22","cited_by_count":18,"area":"agents"},{"id":"2505.17767","title":"Position: The Real Barrier to LLM Agent Usability is Agentic ROI","created":"2025-05-23","cited_by_count":12,"area":"agents"},{"id":"2506.07388","title":"Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents","created":"2025-06-09","cited_by_count":12,"area":"agents"},{"id":"2602.15669","title":"PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2506.01839","title":"Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research","created":"2025-06-02","cited_by_count":10,"area":"agents"},{"id":"2511.16669","title":"Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO","created":"2025-11-20","cited_by_count":9,"area":"lr"},{"id":"2505.22368","title":"AgentDNS: A Root Domain Naming System for LLM Agents","created":"2025-05-28","cited_by_count":8,"area":"agents"},{"id":"2510.10182","title":"A Survey of Inductive Reasoning for Large Language Models","created":"2025-10-11","cited_by_count":8,"area":"lr"},{"id":"2603.02216","title":"ATPO: Adaptive Tree Policy Optimization for Multi-Turn Medical Dialogue","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2509.23573","title":"Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2505.16832","title":"From EduVisBench to EduVisAgent: A Benchmark and Multi-Agent Framework for Reasoning-Driven Pedagogical Visualization","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2512.02321","title":"LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems","created":"2025-12-02","cited_by_count":5,"area":"agents"},{"id":"2601.11650","title":"Large Language Model Agent for User-friendly Chemical Process Simulations","created":"2026-01-15","cited_by_count":5,"area":null},{"id":"2507.13814","title":"CodeEdu: A Multi-Agent Collaborative Platform for Personalized Coding Education","created":"2025-07-18","cited_by_count":4,"area":"agents"},{"id":"2510.09724","title":"InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2511.00382","title":"Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs","created":"2025-11-01","cited_by_count":4,"area":null},{"id":"2512.20206","title":"TongSIM: A General Platform for Simulating Intelligent Machines","created":"2025-12-23","cited_by_count":4,"area":"mllm"},{"id":"2602.16891","title":"OpenSage: Self-programming Agent Generation Engine","created":"2026-02-18","cited_by_count":4,"area":"agents"},{"id":"2602.09416","title":"Are Language Models Sensitive to Morally Irrelevant Distractors?","created":"2026-02-10","cited_by_count":3,"area":null},{"id":"2504.18603","title":"Toward Personalizing Quantum Computing Education: An Evolutionary LLM-Powered Approach","created":"2025-04-24","cited_by_count":2,"area":null},{"id":"2508.11062","title":"Human-in-the-Loop Systems for Adaptive Learning Using Generative AI","created":"2025-08-14","cited_by_count":2,"area":null},{"id":"2510.01164","title":"Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfare","created":"2025-10-01","cited_by_count":2,"area":"agents"},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2604.26962","title":"DeepTutor: Towards Agentic Personalized Tutoring","created":"2026-04-10","cited_by_count":2,"area":"agents"},{"id":"2605.29640","title":"VikingMem: A Memory Base Management System for Stateful LLM-based Applications","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2506.09822","title":"Superstudent intelligence in thermodynamics","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2507.19699","title":"Towards Inclusive NLP: Assessing Compressed Multilingual Transformers across Diverse Language Benchmarks","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2508.20333","title":"Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2511.04706","title":"Prioritize Economy or Climate Action? Investigating ChatGPT Response Differences Based on Inferred Political Orientation","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2511.18221","title":"Enhancing Large Language Models for Automated Homework Assessment in Undergraduate Circuit Analysis","created":"2025-11-22","cited_by_count":1,"area":"mechinterp"},{"id":"2512.04868","title":"SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs","created":"2025-12-04","cited_by_count":1,"area":"lr"},{"id":"2602.18451","title":"Developing a Multi-Agent System to Generate Next Generation Science Assessments with Evidence-Centered Design","created":"2026-02-03","cited_by_count":1,"area":"agents"},{"id":"2603.11375","title":"How do AI agents talk about science and research? An exploration of scientific discussions on Moltbook using BERTopic","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.26328","title":"DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysis","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2605.28369","title":"CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdict","created":"2026-05-27","cited_by_count":1,"area":"agents"},{"id":"2605.31558","title":"Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2606.25358","title":"Agentic Knowledge Tracing: A Multi-Agent LLM Architecture for Stealth Assessment of Financial Literacy in Serious Games","created":"2026-06-24","cited_by_count":1,"area":"agents"},{"id":"2607.13099","title":"WaterMoE: Expert-Routing-based Watermarking for High Fidelity and Efficiency","created":"2026-07-14","cited_by_count":1,"area":"moe"},{"id":"2509.23803","title":"FedAgentBench: Towards Automating Real-world Federated Medical Image Analysis with Server-Client LLM Agents","created":"2025-09-28","cited_by_count":0,"area":"agents"},{"id":"2510.07456","title":"ExpertAgent: Enhancing Personalized Education through Dynamic Planning and Retrieval-Augmented Long-Chain Reasoning","created":"2025-10-08","cited_by_count":0,"area":"lr"},{"id":"2511.03727","title":"MazeMate: An LLM-Powered Chatbot to Support Computational Thinking in Gamified Programming Learning","created":"2025-09-24","cited_by_count":0,"area":"lr"},{"id":"2512.10441","title":"Decoding Student Minds: Leveraging Conversational Agents for Psychological and Learning Analysis","created":"2025-12-11","cited_by_count":0,"area":"agents"},{"id":"2605.02933","title":"Relation Reasoning with LLMs in Expensive Optimization","created":"2026-04-30","cited_by_count":0,"area":"lr"},{"id":"2606.18976","title":"CAPRA: Scaling Feedback on Software Architecture Deliverables with a Multi-Agent LLM System","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2606.20713","title":"FairTutor: Equity-Aware Pedagogical LLM Routing for Budget-Constrained AI Tutoring","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.01247","title":"LLMs as Teaching Assistants for Mathematics Exam Grading: Reliability, and Practical Usability","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2608.25775","title":"ToST: A Tree-of-Thought Socratic Teaching Framework for Multi-Path Guidance and Parallel Thinking","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2608.30288","title":"Extracting Knowledge from Tools in LLM Agents","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.04715","title":"PLUME: Parameter-Efficient Personalization of Large Language Models via Low-Rank User Modulation in Shared Subspaces","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.18274","title":"I code or AI code: A comparative evaluation of AI-rated scores in classroom observations","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.33634","title":"Safety Reconstructed: Generative Modeling via Masked Diffusion Builds Strong Safety Guardrails","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2610.00061","title":"Gradient-Aligned Pair Selection for Personalized Preference Optimization","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}