{"total":71,"rows":[{"id":"2502.05111","title":"Flexible and Efficient Grammar-Constrained Decoding","created":"2025-02-07","cited_by_count":43,"area":null},{"id":"2502.18878","title":"Learning to Generate Structured Output with Schema Reinforcement Learning","created":"2025-02-26","cited_by_count":29,"area":"lr"},{"id":"2506.10896","title":"BioClinical ModernBERT: A State-of-the-Art Long-Context Encoder for Biomedical and Clinical NLP","created":"2025-06-12","cited_by_count":28,"area":null},{"id":"2505.04016","title":"SLOT: Structuring the Output of Large Language Models","created":"2025-05-06","cited_by_count":18,"area":null},{"id":"2506.05754","title":"Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective","created":"2025-06-06","cited_by_count":14,"area":null},{"id":"2505.15389","title":"Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study","created":"2025-05-21","cited_by_count":12,"area":"mllm"},{"id":"2606.01926","title":"Mitigating Bias in Locally Constrained Decoding via Tractable Proposals","created":"2026-06-01","cited_by_count":8,"area":null},{"id":"2511.21750","title":"SO-Bench: A Structural Output Evaluation of Multimodal LLMs","created":"2025-11-23","cited_by_count":6,"area":"mllm"},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2602.14743","title":"LLMStructBench: Benchmarking Large Language Model Structured Data Extraction","created":"2026-02-16","cited_by_count":5,"area":null},{"id":"2503.24191","title":"When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output","created":"2025-03-31","cited_by_count":4,"area":"safety"},{"id":"2505.01954","title":"Semantic Probabilistic Control of Language Models","created":"2025-05-04","cited_by_count":4,"area":null},{"id":"2603.15118","title":"VAREX: A Benchmark for Multi-Modal Structured Extraction from Documents","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2605.06068","title":"VibeServe: Can AI Agents Build Bespoke LLM Serving Systems?","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2510.01902","title":"Constrained Adaptive Rejection Sampling","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2604.03616","title":"The Format Tax","created":"2026-04-04","cited_by_count":3,"area":null},{"id":"2605.29313","title":"PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration","created":"2026-05-28","cited_by_count":3,"area":"agents"},{"id":"2508.03611","title":"Astrolabe: Balancing Load in LLM Serving with Randomized Prediction-Guided Scheduling","created":"2025-08-05","cited_by_count":2,"area":"inference"},{"id":"2603.22015","title":"Retrieving Climate Change Disinformation by Narrative","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2605.08737","title":"The Extrapolation Cliff in On-Policy Distillation of Near-Deterministic Structured Outputs","created":"2026-05-09","cited_by_count":2,"area":"distill"},{"id":"2605.12729","title":"Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety","created":"2026-05-12","cited_by_count":2,"area":"agents"},{"id":"2608.08254","title":"Your Prompt Is Not the Only Prompt: How Much Do LLMs Weight Structured-Output Schema Descriptions?","created":"2026-08-08","cited_by_count":2,"area":null},{"id":"2603.05540","title":"Attention Meets Reachability: Structural Equivalence and Efficiency in Grammar-Constrained LLM Decoding","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2603.10002","title":"SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2603.19500","title":"Teaching an Agent to Sketch One Part at a Time","created":"2026-03-19","cited_by_count":1,"area":"agents"},{"id":"2603.26728","title":"SEAR: Schema-Based Evaluation and Routing for LLM Gateways","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2604.20811","title":"Diagnosing CFG Interpretation in LLMs","created":"2026-04-22","cited_by_count":1,"area":"agents"},{"id":"2605.02363","title":"When Correct Isn't Usable: Improving Structured Output Reliability in Small Language Models","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.16342","title":"DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.26731","title":"It's Not the Capability: Harness Sensitivity Is Non-Monotone Across LLM Agent Tiers","created":"2026-05-26","cited_by_count":1,"area":"agents"},{"id":"2606.31808","title":"Large Databases Need Small, Open-Weight Language Models","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2610.07086","title":"SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding","created":"2026-10-05","cited_by_count":1,"area":"agents"},{"id":"2506.23394","title":"Teaching a Language Model to Speak the Language of Tools","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2507.06565","title":"A Mathematical Theory of Discursive Networks","created":"2025-07-09","cited_by_count":0,"area":null},{"id":"2508.01159","title":"Asking the Right Questions: Benchmarking Large Language Models in the Development of Clinical Consultation Templates","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2509.25922","title":"DeepJSONEval: Benchmarking Complex Nested JSON Data Mining for Large Language Models","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2511.01720","title":"Efficient Tool-Calling Multi-Expert NPC Agent for Commonsense Persona-Grounded Dialogue","created":"2025-11-03","cited_by_count":0,"area":"agents"},{"id":"2512.14761","title":"CAPE: Capability Achievement via Policy Execution","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2512.19305","title":"CienaLLM: Generative Climate-Impact Extraction from News Articles with Autoregressive LLMs","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2602.12468","title":"Continuous Diffusion Models Can Obey Formal Syntax","created":"2026-02-12","cited_by_count":0,"area":"diffusion"},{"id":"2602.15189","title":"ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2603.09448","title":"A Guideline-Aware AI Agent for Zero-Shot Target Volume Auto-Delineation","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2605.00060","title":"TADI: Tool-Augmented Drilling Intelligence via Agentic LLM Orchestration over Heterogeneous Wellsite Data","created":"2026-04-30","cited_by_count":0,"area":"agents"},{"id":"2605.14051","title":"SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks","created":"2026-05-13","cited_by_count":0,"area":"agents"},{"id":"2606.08715","title":"Operationalizing Linguistic Methods through Prompt-Engineering Skills: An Automatic Chinese Web Neologism Detection Pipeline","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.20072","title":"STAGE: Source-grounded Text-to-JSON Artifact GEneration","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.21453","title":"CORTIS: Text-Only Adaptation of Spoken Language Models for Task-Oriented Voice Agents","created":"2026-06-19","cited_by_count":0,"area":"agents"},{"id":"2607.04694","title":"Solve the Missing First Step: Can VLMs Standardize Raw Heterogeneous Medical Data?","created":"2026-07-06","cited_by_count":0,"area":"mllm"},{"id":"2607.06757","title":"LLM-powered reasoning in agent-based modeling","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2607.08268","title":"Different Teachers, Different Capabilities: Sub-1B On-Device Distillation for Structured Text Enrichment","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.09791","title":"Gauge dependence and structured-output corruption in sign-branched repetition penalties: measurements across models, inference stacks, and alternative repetition controls","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.10187","title":"Knowledge-Conditioned, Single-Pass LLM Synthesis of Executable Unity Game Scenes: A Compiler Error Census across 26 Goal Playable Concepts","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.17917","title":"PEARL: Auditable Repair for Scientific Reasoning Graph Extraction","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2607.19297","title":"Graph-Based Agentic AI with LangGraph: Workflow Pathways for Long-Running Stateful Business Processes","created":"2026-07-21","cited_by_count":0,"area":"agents"},{"id":"2607.21756","title":"Prompt as a Data Type: In-Database LLM Prompt Management and Rewriting","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2608.06167","title":"Schema-Guided Hierarchical Information Extraction and Semantic Evaluation Using Generative AI","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.12574","title":"Trie Automata for Constrained Decoding over Large Finite Sets","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.23026","title":"Beyond Surface Cues: Disentangling Sociocultural Signals in Multilingual LLMs","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.25358","title":"Right Values, Wrong Places: Diagnosing and Fixing Record Misplacement in LLM-Generated JSON","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.10016","title":"MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.23742","title":"Constrained Decoding Eliminates Structural Failures in Small LLMs but Reveals a Scale-Dependent Semantic Gap","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.29947","title":"Neuro-symbolic AI for Industrial Configuration","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.34366","title":"When Harness Beats Scale, and When Reading Beats Both","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.40185","title":"Provably Tractable NFA-Constrained Language Generation via HMMs","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00328","title":"ContractRL: Shielded Group-Relative Policy Optimization for Auditable Tool-Call Repair","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00437","title":"JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.02001","title":"Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.06425","title":"SoK: Semantic Decision Engines in Network Control Loops","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.08106","title":"ChartBmkAgent: Harness-Governed Multi-Agent Construction of Chart QA Benchmarks from Sparse Error-Taxonomy Specifications","created":"2026-10-06","cited_by_count":0,"area":"mllm"},{"id":"2610.16191","title":"Correct Choices, Failed Sequences: Choice2Seq Benchmarks Correctness Retention Across Output Interfaces","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17643","title":"When Should Enterprise Policy Decisions Be Learned, and When Should They Be Reasoned?","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}