{"total":105,"rows":[{"id":"2312.07104","title":"SGLang: Efficient Execution of Structured Language Model Programs","created":"2023-12-12","cited_by_count":1141,"area":null},{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431,"area":"agents"},{"id":"2412.13171","title":"Compressed Chain of Thought: Efficient Reasoning Through Dense Representations","created":"2024-12-17","cited_by_count":201,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2311.04254","title":"Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation","created":"2023-11-07","cited_by_count":74,"area":"lr"},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2401.14295","title":"Demystifying Chains, Trees, and Graphs of Thoughts","created":"2024-01-25","cited_by_count":63,"area":"lr"},{"id":"2510.03215","title":"Cache-to-Cache: Direct Semantic Communication Between Large Language Models","created":"2025-10-03","cited_by_count":61,"area":"inference"},{"id":"2504.15466","title":"Learning Adaptive Parallel Reasoning with Language Models","created":"2025-04-21","cited_by_count":58,"area":"lr"},{"id":"2505.16192","title":"VLM-R$^3$: Region Recognition, Reasoning, and Refinement for Enhanced Multimodal Chain-of-Thought","created":"2025-05-22","cited_by_count":49,"area":"lr"},{"id":"2412.19509","title":"MBQ: Modality-Balanced Quantization for Large Vision-Language Models","created":"2024-12-27","cited_by_count":45,"area":"mllm"},{"id":"2502.16235","title":"Dynamic Parallel Tree Search for Efficient LLM Reasoning","created":"2025-02-22","cited_by_count":42,"area":"lr"},{"id":"2504.06261","title":"Hogwild! Inference: Parallel LLM Generation via Concurrent Attention","created":"2025-04-08","cited_by_count":32,"area":"inference"},{"id":"2508.08712","title":"A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models","created":"2025-08-12","cited_by_count":30,"area":"diffusion"},{"id":"2412.16545","title":"Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models","created":"2024-12-21","cited_by_count":26,"area":null},{"id":"2505.17941","title":"VeriThinker: Learning to Verify Makes Reasoning Model Efficient","created":"2025-05-23","cited_by_count":24,"area":"lr"},{"id":"2311.14109","title":"Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training","created":"2023-11-23","cited_by_count":22,"area":"lr"},{"id":"2402.01521","title":"K-Level Reasoning: Establishing Higher Order Beliefs in Large Language Models for Strategic Reasoning","created":"2024-02-02","cited_by_count":21,"area":"lr"},{"id":"2502.00409","title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","created":"2025-02-01","cited_by_count":20,"area":null},{"id":"2403.11236","title":"ChartThinker: A Contextual Chain-of-Thought Approach to Optimized Chart Summarization","created":"2024-03-17","cited_by_count":19,"area":"lr"},{"id":"2412.17153","title":"Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching","created":"2024-12-22","cited_by_count":18,"area":"diffusion"},{"id":"2505.22017","title":"The Price of a Second Thought: On the Evaluation of Reasoning Efficiency in Large Language Models","created":"2025-05-28","cited_by_count":18,"area":"lr"},{"id":"2602.09341","title":"Auditing Multi-Agent LLM Reasoning Trees Outperforms Majority Vote and LLM-as-Judge","created":"2026-02-10","cited_by_count":18,"area":"lr"},{"id":"2501.14304","title":"MASTER: A Multi-Agent System with LLM Specialized MCTS","created":"2025-01-24","cited_by_count":16,"area":"agents"},{"id":"2509.25035","title":"Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct","created":"2025-09-29","cited_by_count":16,"area":"diffusion"},{"id":"2405.17438","title":"An LLM-Tool Compiler for Fused Parallel Function Calling","created":"2024-05-07","cited_by_count":15,"area":"lr"},{"id":"2507.08944","title":"Optimizing Sequential Multi-Step Tasks with Parallel LLM Agents","created":"2025-07-11","cited_by_count":14,"area":"agents"},{"id":"2510.24051","title":"Pie: A Programmable Serving System for Emerging LLM Applications","created":"2025-10-28","cited_by_count":14,"area":"lr"},{"id":"2511.06134","title":"Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMs","created":"2025-11-08","cited_by_count":14,"area":"agents"},{"id":"2603.22862","title":"The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration","created":"2026-03-24","cited_by_count":14,"area":"agents"},{"id":"2504.07081","title":"Self-Steering Language Models","created":"2025-04-09","cited_by_count":13,"area":"lr"},{"id":"2506.05333","title":"Kinetics: Rethinking Test-Time Scaling Laws","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2509.16736","title":"Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach","created":"2025-09-20","cited_by_count":12,"area":"agents"},{"id":"2402.16844","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding","created":"2024-02-26","cited_by_count":11,"area":"lr"},{"id":"2504.00424","title":"Hawkeye:Efficient Reasoning with Model Collaboration","created":"2025-04-01","cited_by_count":11,"area":"lr"},{"id":"2508.08895","title":"ASPD: Unlocking Adaptive Serial-Parallel Decoding by Exploring Intrinsic Parallelism in LLMs","created":"2025-08-12","cited_by_count":11,"area":"inference"},{"id":"2410.04463","title":"Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information","created":"2024-10-06","cited_by_count":10,"area":"lr"},{"id":"2504.02181","title":"A Survey of Scaling in Large Language Model Reasoning","created":"2025-04-02","cited_by_count":10,"area":"lr"},{"id":"2505.14709","title":"FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge","created":"2025-05-17","cited_by_count":10,"area":null},{"id":"2506.05745","title":"SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models","created":"2025-06-06","cited_by_count":10,"area":"lr"},{"id":"2606.10662","title":"Decentralized Multi-Agent Systems with Shared Context","created":"2026-06-09","cited_by_count":10,"area":"lr"},{"id":"2510.18087","title":"Planned Diffusion","created":"2025-10-20","cited_by_count":9,"area":"diffusion"},{"id":"2512.14044","title":"OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving","created":"2025-12-16","cited_by_count":9,"area":"lr"},{"id":"2603.07972","title":"Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning","created":"2026-03-09","cited_by_count":9,"area":"agents"},{"id":"2604.02985","title":"Prompt Compression in the Wild: Measuring Latency, Rate Adherence, and Quality for Faster LLM Inference","created":"2026-04-03","cited_by_count":9,"area":"rag"},{"id":"2412.11934","title":"Stepwise Reasoning Error Disruption Attack of LLMs","created":"2024-12-16","cited_by_count":8,"area":"lr"},{"id":"2507.21035","title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","created":"2025-07-28","cited_by_count":8,"area":"agents"},{"id":"2601.11340","title":"Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models","created":"2026-01-16","cited_by_count":8,"area":"lr"},{"id":"2505.20625","title":"Long Context Scaling: Divide and Conquer via Multi-Agent Question-driven Collaboration","created":"2025-05-27","cited_by_count":7,"area":"agents"},{"id":"2602.05446","title":"DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors","created":"2026-02-05","cited_by_count":7,"area":"agents"},{"id":"2501.09367","title":"PICE: A Semantic-Driven Progressive Inference System for LLM Serving in Cloud-Edge Networks","created":"2025-01-16","cited_by_count":6,"area":"inference"},{"id":"2503.20533","title":"Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence","created":"2025-03-26","cited_by_count":6,"area":"lr"},{"id":"2407.06112","title":"Enhancing Language Model Rationality with Bi-Directional Deliberation Reasoning","created":"2024-07-08","cited_by_count":5,"area":"lr"},{"id":"2507.02663","title":"Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models","created":"2025-07-03","cited_by_count":5,"area":"lr"},{"id":"2601.22623","title":"SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly","created":"2026-01-30","cited_by_count":5,"area":"agents"},{"id":"2308.11914","title":"Towards CausalGPT: A Multi-Agent Approach for Faithful Knowledge Reasoning via Promoting Causal Consistency in LLMs","created":"2023-08-23","cited_by_count":4,"area":"lr"},{"id":"2506.05387","title":"Advancing Decoding Strategies: Enhancements in Locally Typical Sampling for LLMs","created":"2025-06-03","cited_by_count":4,"area":null},{"id":"2512.17093","title":"A Solver-in-the-Loop Framework for Improving LLMs on Answer Set Programming for Logic Puzzle Solving","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2506.18728","title":"PARALLELPROMPT: Extracting Parallelism from Large Language Model Queries","created":"2025-06-23","cited_by_count":3,"area":"inference"},{"id":"2606.23595","title":"SPIRAL: Learning to Search and Aggregate","created":"2026-06-22","cited_by_count":3,"area":"lr"},{"id":"2403.13112","title":"Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks","created":"2024-03-19","cited_by_count":2,"area":null},{"id":"2509.23322","title":"Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Framework","created":"2025-09-27","cited_by_count":2,"area":"lr"},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2602.13639","title":"Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval","created":"2026-02-14","cited_by_count":2,"area":"lr"},{"id":"2602.14469","title":"Measuring and Mitigating Post-hoc Rationalization in Reverse Chain-of-Thought Generation","created":"2026-02-16","cited_by_count":2,"area":"lr"},{"id":"2603.00030","title":"SimpleTool: Parallel Decoding for Real-Time LLM Function Calling","created":"2026-02-04","cited_by_count":2,"area":"agents"},{"id":"2604.10027","title":"SinkTrack: Attention Sink based Context Anchoring for Large Language Models","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2511.10201","title":"EffiReason-Bench: A Unified Benchmark for Evaluating and Advancing Efficient Reasoning in Large Language Models","created":"2025-11-13","cited_by_count":1,"area":"lr"},{"id":"2601.21619","title":"On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2601.22662","title":"Task-Aware LLM Council with Adaptive Decision Pathways for Decision Support","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2601.23027","title":"Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.16512","title":"Framework of Thoughts: A Foundation Framework for Dynamic and Optimized Reasoning based on Chains, Trees, and Graphs","created":"2026-02-18","cited_by_count":1,"area":"lr"},{"id":"2603.01571","title":"Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models","created":"2026-03-02","cited_by_count":1,"area":"lr"},{"id":"2604.26209","title":"Breaking the Autoregressive Chain: Hyper-Parallel Decoding for Efficient LLM-Based Attribute Value Extraction","created":"2026-04-29","cited_by_count":1,"area":"inference"},{"id":"2606.14674","title":"AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition","created":"2026-06-12","cited_by_count":1,"area":"agents"},{"id":"2607.27578","title":"What makes prompts a graph: necessary and sufficient conditions for prompt graph engineering","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.06146","title":"PaDoc: Layout-Grounded Parallel Decoding for Document Parsing","created":"2026-08-06","cited_by_count":1,"area":"inference"},{"id":"2609.05707","title":"Intra-Prompt Parallel Decoding for Common-Context Question Answering","created":"2026-09-04","cited_by_count":1,"area":"inference"},{"id":"2510.01500","title":"Lateral Tree-of-Thoughts Surpasses ToT by Incorporating Logically-Consistent, Low-Utility Candidates","created":"2025-10-01","cited_by_count":0,"area":"lr"},{"id":"2510.18162","title":"Automatic Prompt Generation via Adaptive Selection of Prompting Techniques","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2510.22978","title":"Reasoning About Reasoning: Towards Informed and Reflective Use of LLM Reasoning in HCI","created":"2025-10-27","cited_by_count":0,"area":"lr"},{"id":"2510.24390","title":"Improving LLM Reasoning via Dependency-Aware Query Decomposition and Logic-Parallel Content Expansion","created":"2025-10-28","cited_by_count":0,"area":"lr"},{"id":"2511.12987","title":"Reuse, Don't Recompute: Efficient Large Reasoning Model Inference via Memory Orchestration","created":"2025-11-17","cited_by_count":0,"area":"lr"},{"id":"2511.15738","title":"Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn","created":"2025-11-18","cited_by_count":0,"area":"lr"},{"id":"2511.20662","title":"Democratizing LLM Efficiency: From Hyperscale Optimizations to Universal Deployability","created":"2025-11-03","cited_by_count":0,"area":"rag"},{"id":"2512.08169","title":"Information-Dense Reasoning for Efficient and Auditable Security Alert Triage","created":"2025-12-09","cited_by_count":0,"area":"lr"},{"id":"2512.10054","title":"Parallel Decoder Transformer: Planner-Conditioned Latent Coordination for Model-Intrinsic Parallel Generation","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2602.06527","title":"HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction","created":"2026-02-06","cited_by_count":0,"area":"lr"},{"id":"2602.22508","title":"Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2603.16867","title":"Efficient Reasoning on the Edge","created":"2026-03-17","cited_by_count":0,"area":"lr"},{"id":"2604.04418","title":"Justified or Just Convincing? Error Verifiability as a Dimension of LLM Quality","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2605.06914","title":"Regulating Branch Parallelism in LLM Serving","created":"2026-05-07","cited_by_count":0,"area":"inference"},{"id":"2605.10195","title":"Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.18697","title":"PopPy: Opportunistically Exploiting Parallelism in Python Agentic Workflows","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.01168","title":"Thinking Economically: A Hierarchical Framework for Adaptive-Complexity Reasoning in LLMs","created":"2026-05-31","cited_by_count":0,"area":"lr"},{"id":"2606.05158","title":"Streaming Communication in Multi-Agent Reasoning","created":"2026-06-03","cited_by_count":0,"area":"lr"},{"id":"2608.18988","title":"DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.21969","title":"ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents","created":"2026-08-22","cited_by_count":0,"area":"alignment"},{"id":"2609.33477","title":"Just Let Linear States Forget the Distant Past: Prefix Caching via Suffix Replay for Hybrid LLMs","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":"100"}