{"total":112,"rows":[{"id":"2506.02153","title":"Small Language Models are the Future of Agentic AI","created":"2025-06-02","cited_by_count":270,"area":"agents"},{"id":"2502.11528","title":"A Survey of Personalized Large Language Models: Progress and Future Directions","created":"2025-02-17","cited_by_count":71,"area":null},{"id":"2505.17612","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","created":"2025-05-23","cited_by_count":47,"area":"lr"},{"id":"2412.18116","title":"AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation","created":"2024-12-24","cited_by_count":34,"area":"agents"},{"id":"2410.17215","title":"MiniPLM: Knowledge Distillation for Pre-Training Language Models","created":"2024-10-22","cited_by_count":29,"area":"distill"},{"id":"2502.11569","title":"Towards Reasoning Ability of Small Language Models","created":"2025-02-17","cited_by_count":29,"area":"lr"},{"id":"2502.04392","title":"Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents","created":"2025-02-06","cited_by_count":25,"area":"lr"},{"id":"2504.17119","title":"The Rise of Small Language Models in Healthcare: A Comprehensive Survey","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2410.01805","title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices","created":"2024-10-02","cited_by_count":15,"area":"inference"},{"id":"2504.04718","title":"T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models","created":"2025-04-07","cited_by_count":13,"area":"lr"},{"id":"2505.16508","title":"Edge-First Language Model Inference: Models, Metrics, and Tradeoffs","created":"2025-05-22","cited_by_count":13,"area":null},{"id":"2502.00641","title":"Evaluating Small Language Models for News Summarization: Implications and Factors Influencing Performance","created":"2025-02-02","cited_by_count":12,"area":null},{"id":"2503.16788","title":"Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study","created":"2025-03-21","cited_by_count":11,"area":"lr"},{"id":"2504.11514","title":"Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models","created":"2025-04-15","cited_by_count":11,"area":"driving"},{"id":"2505.21594","title":"Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exits","created":"2025-05-27","cited_by_count":11,"area":"inference"},{"id":"2501.03265","title":"Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment","created":"2025-01-04","cited_by_count":10,"area":"lr"},{"id":"2503.00686","title":"GPIoT: Tailoring Small Language Models for IoT Program Synthesis and Development","created":"2025-03-02","cited_by_count":10,"area":null},{"id":"2503.16585","title":"Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions","created":"2025-03-20","cited_by_count":10,"area":"mllm"},{"id":"2507.22478","title":"SLM-SQL: An Exploration of Small Language Models for Text-to-SQL","created":"2025-07-30","cited_by_count":10,"area":null},{"id":"2508.13023","title":"G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance","created":"2025-08-18","cited_by_count":10,"area":"lr"},{"id":"2502.10993","title":"RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization","created":"2025-02-16","cited_by_count":9,"area":"rag"},{"id":"2503.10573","title":"Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approach","created":"2025-03-13","cited_by_count":8,"area":"lr"},{"id":"2411.05046","title":"PhoneLM:an Efficient and Capable Small Language Model Family through Principled Pre-training","created":"2024-11-07","cited_by_count":7,"area":null},{"id":"2502.11100","title":"Towards Achieving Concept Completeness for Textual Concept Bottleneck Models","created":"2025-02-16","cited_by_count":7,"area":null},{"id":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2412.00402","title":"DroidCall: A Dataset for LLM-powered Android Intent Invocation","created":"2024-11-30","cited_by_count":5,"area":"agents"},{"id":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2506.06579","title":"Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2601.00588","title":"CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns","created":"2026-01-02","cited_by_count":5,"area":"safety"},{"id":"2604.07003","title":"EmoMAS: Emotion-Aware Multi-Agent System for High-Stakes Edge-Deployable Negotiation with Bayesian Orchestration","created":"2026-04-08","cited_by_count":5,"area":"agents"},{"id":"2503.09579","title":"Cost-Optimal Grouped-Query Attention for Long-Context Modeling","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2503.12167","title":"PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing","created":"2025-03-15","cited_by_count":4,"area":null},{"id":"2509.05818","title":"Chatbot To Help Patients Understand Their Health","created":"2025-09-06","cited_by_count":4,"area":null},{"id":"2511.05184","title":"Effectiveness of Chain-of-Thought in Distilling Reasoning Capability from Large Language Models","created":"2025-11-07","cited_by_count":4,"area":"lr"},{"id":"2603.06713","title":"Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces","created":"2026-03-05","cited_by_count":4,"area":"agents"},{"id":"2503.06019","title":"GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices","created":"2025-03-08","cited_by_count":3,"area":"mllm"},{"id":"2503.06519","title":"Can Small Language Models Reliably Resist Jailbreak Attacks? A Comprehensive Evaluation","created":"2025-03-09","cited_by_count":3,"area":"safety"},{"id":"2505.06461","title":"Challenging GPU Dominance: When CPUs Outperform for On-Device LLM Inference","created":"2025-05-09","cited_by_count":3,"area":null},{"id":"2506.13404","title":"Effective Learning for Small Reasoning Models: An Empirical Study on 0.5B Reasoning LLMs","created":"2025-06-16","cited_by_count":3,"area":"lr"},{"id":"2508.11834","title":"Recent Advances in Transformer and Large Language Models for UAV Applications","created":"2025-08-15","cited_by_count":3,"area":null},{"id":"2512.02716","title":"Menta: A Small Language Model for On-Device Mental Health Prediction","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2501.05478","title":"Language and Planning in Robotic Navigation: A Multilingual Evaluation of State-of-the-Art Models","created":"2025-01-07","cited_by_count":2,"area":null},{"id":"2502.04747","title":"Every Software as an Agent: Blueprint and Case Study","created":"2025-02-07","cited_by_count":2,"area":"agents"},{"id":"2502.19883","title":"Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models","created":"2025-02-27","cited_by_count":2,"area":"safety"},{"id":"2506.15687","title":"S$^2$GPT-PINNs: Sparse and Small models for PDEs","created":"2025-05-25","cited_by_count":2,"area":null},{"id":"2508.20324","title":"Can Compact Language Models Search Like Agents? Distillation-Guided Policy Optimization for Preserving Agentic RAG Capabilities","created":"2025-08-27","cited_by_count":2,"area":"agents"},{"id":"2509.04518","title":"Advancing SLM Tool-Use Capability using Reinforcement Learning","created":"2025-09-03","cited_by_count":2,"area":"lr"},{"id":"2510.05858","title":"DACP: Domain-Adaptive Continual Pre-Training of Large Language Models for Phone Conversation Summarization","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.08600","title":"Recover-LoRA: Data-Free Accuracy Recovery of Degraded Language Models via Low-Rank Adaptation","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2511.03370","title":"EQ-Negotiator: Dynamic Emotional Personas Empower Small Language Models for Edge-Deployable Credit Negotiation","created":"2025-11-05","cited_by_count":2,"area":null},{"id":"2603.15421","title":"CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agents","created":"2026-03-16","cited_by_count":2,"area":"agents"},{"id":"2606.25191","title":"To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG","created":"2026-06-23","cited_by_count":2,"area":"rag"},{"id":"2411.06402","title":"Fineweb-Edu-Ar: Machine-translated Corpus to Support Arabic Small Language Models","created":"2024-11-10","cited_by_count":1,"area":null},{"id":"2412.14501","title":"Do Large Language Models Advocate for Inferentialism?","created":"2024-12-19","cited_by_count":1,"area":null},{"id":"2503.01869","title":"From Small to Large Language Models: Revisiting the Federalist Papers","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2504.07965","title":"Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments","created":"2025-04-10","cited_by_count":1,"area":"alignment"},{"id":"2506.07424","title":"Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2506.13772","title":"MobiEdit: Resource-efficient Knowledge Editing for Personalized On-device LLMs","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2507.06795","title":"ixi-GEN: Efficient Industrial sLLMs through Domain Adaptive Continual Pretraining","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2508.01268","title":"Win-k: Improved Membership Inference Attacks on Small Language Models","created":"2025-08-02","cited_by_count":1,"area":"safety"},{"id":"2601.11553","title":"PerCache: Predictive Hierarchical Cache for RAG Applications on Mobile Devices","created":"2025-12-10","cited_by_count":1,"area":"rag"},{"id":"2602.00887","title":"EffGen: Enabling Small Language Models as Capable Autonomous Agents","created":"2026-01-31","cited_by_count":1,"area":"agents"},{"id":"2603.28817","title":"GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models","created":"2026-03-28","cited_by_count":1,"area":"safety"},{"id":"2605.30102","title":"When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems","created":"2026-05-28","cited_by_count":1,"area":"agents"},{"id":"2606.21428","title":"Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study","created":"2026-06-19","cited_by_count":1,"area":"moe"},{"id":"2606.24689","title":"Automated Summarization of Software Documents: An LLM-based Multi-Agent Approach","created":"2026-06-23","cited_by_count":1,"area":"agents"},{"id":"2607.03801","title":"Punching Above Their Weight: Classification-Head Fine-Tuning of Tiny Language Models (TLMs) for Verifiable Multiple-Choice Tasks","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2607.20216","title":"Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware Analysis","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2412.19638","title":"Xmodel-2 Technical Report","created":"2024-12-27","cited_by_count":0,"area":"lr"},{"id":"2506.03822","title":"CRAWLDoc: A Dataset for Robust Ranking of Bibliographic Documents","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2506.07695","title":"Towards a Small Language Model Lifecycle Framework","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2506.12403","title":"Bridging the Digital Divide: Small Language Models as a Pathway for Physics and Photonics Education in Underdeveloped Regions","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2506.13514","title":"TensorSLM: Energy-efficient Embedding Compression of Sub-billion Parameter Language Models on Low-end Devices","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2506.17019","title":"Instituto de Telecomunica\\c{c}\\~oes at IWSLT 2025: Aligning Small-Scale Speech and Language Models for Speech-to-Text Learning","created":"2025-06-20","cited_by_count":0,"area":null},{"id":"2506.22486","title":"Hallucination Detection with Small Language Models","created":"2025-06-24","cited_by_count":0,"area":"rag"},{"id":"2509.00680","title":"Do small language models generate realistic variable-quality fake news headlines?","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2509.16633","title":"When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs","created":"2025-09-20","cited_by_count":0,"area":"mllm"},{"id":"2510.03913","title":"PsycholexTherapy: Simulating Reasoning in Psychotherapy with Small Language Models in Persian","created":"2025-10-04","cited_by_count":0,"area":"lr"},{"id":"2510.24150","title":"Ko-MuSR: A Multistep Soft Reasoning Benchmark for LLMs Capable of Understanding Korean","created":"2025-10-28","cited_by_count":0,"area":"lr"},{"id":"2511.03466","title":"Kastor: Fine-tuned Small Language Models for Shape-based Active Relation Extraction","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2511.05915","title":"CoEdge-RAG: Optimizing Hierarchical Scheduling for Retrieval-Augmented LLMs in Collaborative Edge Computing","created":"2025-11-08","cited_by_count":0,"area":"rag"},{"id":"2512.18622","title":"A Multi-agent Text2SQL Framework using Small Language Models and Execution Feedback","created":"2025-12-21","cited_by_count":0,"area":"agents"},{"id":"2602.02632","title":"Performance of Small Language Model Pretraining on FABRIC: An Empirical Study","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.10869","title":"Agentic Knowledge Distillation: Autonomous Training of Small Language Models for SMS Threat Detection","created":"2026-02-11","cited_by_count":0,"area":"agents"},{"id":"2603.21419","title":"Is the future of AI green? What can innovation diffusion models say about generative AI's environmental impact?","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.02367","title":"Evaluating Small Language Models for Front-Door Routing: A Harmonized Benchmark and Synthetic-Traffic Experiment","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.06562","title":"On Emotion-Sensitive Decision Making of Small Language Model Agents","created":"2026-04-08","cited_by_count":0,"area":"agents"},{"id":"2604.11512","title":"EdgeCIM: A Hardware-Software Co-Design for CIM-Based Acceleration of Small Language Models","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.12301","title":"Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads","created":"2026-04-14","cited_by_count":0,"area":"agents"},{"id":"2604.15357","title":"Taming Asynchronous CPU-GPU Coupling for Frequency-aware Latency Estimation on Mobile Edge","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2604.17450","title":"Compiling Deterministic Structure into SLM Harnesses","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2604.23809","title":"LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models","created":"2026-04-26","cited_by_count":0,"area":"lr"},{"id":"2605.07731","title":"Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs","created":"2026-05-08","cited_by_count":0,"area":"moe"},{"id":"2605.25394","title":"Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2607.14149","title":"Enhancing Small Language Models Reasoning through Knowledge Graph Grounding","created":"2026-07-14","cited_by_count":0,"area":"lr"},{"id":"2607.18819","title":"In-Context Learning for Wound Classification with Small Multimodal Language Models","created":"2026-07-21","cited_by_count":0,"area":"mllm"},{"id":"2607.22556","title":"MIITA: Memory-Induced Inference-Time Adaptation for Continual Learning with Small Language Models","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2608.00042","title":"Trustworthiness Costs of Domain Adaptation in Small Language Models:A Cross-Architecture Empirical Study","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.04488","title":"Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.06609","title":"Automated item evaluation: Predicting item acceptance and rejection using LLM-generated critiques","created":"2026-08-06","cited_by_count":0,"area":null}],"next_cursor":"100"}