{"total":96,"rows":[{"id":"2409.03215","title":"xLAM: A Family of Large Action Models to Empower AI Agent Systems","created":"2024-09-05","cited_by_count":111,"area":"agents"},{"id":"2410.23266","title":"TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models","created":"2024-10-30","cited_by_count":73,"area":"lr"},{"id":"2501.10868","title":"JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Models","created":"2025-01-18","cited_by_count":71,"area":null},{"id":"2506.23719","title":"DABstep: Data Agent Benchmark for Multi-step Reasoning","created":"2025-06-30","cited_by_count":46,"area":"lr"},{"id":"2502.05111","title":"Flexible and Efficient Grammar-Constrained Decoding","created":"2025-02-07","cited_by_count":43,"area":null},{"id":"2502.15631","title":"The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer","created":"2025-02-21","cited_by_count":41,"area":"lr"},{"id":"2502.18878","title":"Learning to Generate Structured Output with Schema Reinforcement Learning","created":"2025-02-26","cited_by_count":29,"area":"lr"},{"id":"2408.08656","title":"LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs","created":"2024-08-16","cited_by_count":25,"area":null},{"id":"2410.03524","title":"Steering Large Language Models between Code Execution and Textual Reasoning","created":"2024-10-04","cited_by_count":24,"area":"lr"},{"id":"2408.11061","title":"StructuredRAG: JSON Response Formatting with Large Language Models","created":"2024-08-07","cited_by_count":22,"area":null},{"id":"2410.03837","title":"Learning Code Preference via Synthetic Evolution","created":"2024-10-04","cited_by_count":19,"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":"2410.10336","title":"CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning","created":"2024-10-14","cited_by_count":16,"area":"lr"},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"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":"2507.10541","title":"REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once","created":"2025-07-14","cited_by_count":12,"area":"lr"},{"id":"2505.22169","title":"ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Moments","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2509.19236","title":"AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration","created":"2025-09-23","cited_by_count":10,"area":"agents"},{"id":"2409.18216","title":"MMMT-IF: A Challenging Multimodal Multi-Turn Instruction Following Benchmark","created":"2024-09-26","cited_by_count":8,"area":null},{"id":"2505.20645","title":"STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Models","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2510.11586","title":"Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2601.06993","title":"Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?","created":"2026-01-11","cited_by_count":8,"area":"lr"},{"id":"2502.01683","title":"LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2502.05867","title":"Self-Training Large Language Models for Tool-Use Without Demonstrations","created":"2025-02-09","cited_by_count":7,"area":"lr"},{"id":"2507.05517","title":"Empowering Healthcare Practitioners with Language Models: Structuring Speech Transcripts in Two Real-World Clinical Applications","created":"2025-07-07","cited_by_count":7,"area":null},{"id":"2509.19841","title":"ThinkFake: Reasoning in Multimodal Large Language Models for AI-Generated Image Detection","created":"2025-09-24","cited_by_count":7,"area":"lr"},{"id":"2409.18594","title":"\"Oh LLM, I'm Asking Thee, Please Give Me a Decision Tree\": Zero-Shot Decision Tree Induction and Embedding with Large Language Models","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2411.00852","title":"EF-LLM: Energy Forecasting LLM with AI-assisted Automation, Enhanced Sparse Prediction, Hallucination Detection","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2503.01923","title":"Output Length Effect on DeepSeek-R1's Safety in Forced Thinking","created":"2025-03-02","cited_by_count":6,"area":"lr"},{"id":"2607.01456","title":"From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills","created":"2026-07-01","cited_by_count":6,"area":"agents"},{"id":"2509.21791","title":"Quantifying the Impact of Structured Output Format on Large Language Models through Causal Inference","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2608.13317","title":"StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems","created":"2026-08-13","cited_by_count":5,"area":"agents"},{"id":"2410.23902","title":"Responsible Retrieval Augmented Generation for Climate Decision Making from Documents","created":"2024-10-31","cited_by_count":4,"area":"rag"},{"id":"2503.11858","title":"OpeNLGauge: An Explainable Metric for NLG Evaluation with Open-Weights LLMs","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2505.07155","title":"Reassessing Large Language Model Boolean Query Generation for Systematic Reviews","created":"2025-05-12","cited_by_count":4,"area":null},{"id":"2506.11266","title":"Live API-Bench: 2500+ Live APIs for Testing Multi-Step Tool Calling","created":"2025-06-12","cited_by_count":4,"area":"agents"},{"id":"2509.19358","title":"Benchmarking and Improving LLM Robustness for Personalized Generation","created":"2025-09-18","cited_by_count":4,"area":null},{"id":"2510.00024","title":"EpidemIQs: Prompt-to-Paper LLM Agents for Epidemic Modeling and Analysis","created":"2025-09-24","cited_by_count":4,"area":"agents"},{"id":"2409.03346","title":"Sketch: A Toolkit for Streamlining LLM Operations","created":"2024-09-05","cited_by_count":3,"area":null},{"id":"2502.12516","title":"Can LLMs Extract Frame-Semantic Arguments?","created":"2025-02-18","cited_by_count":3,"area":null},{"id":"2505.01485","title":"CHORUS: Zero-shot Hierarchical Retrieval and Orchestration for Generating Linear Programming Code","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2510.01902","title":"Constrained Adaptive Rejection Sampling","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2609.32160","title":"Typed Decision Models: An Early Evidence Audit and Evaluation Checklist","created":"2026-09-26","cited_by_count":3,"area":null},{"id":"2502.00032","title":"Querying Databases with Function Calling","created":"2025-01-23","cited_by_count":2,"area":"agents"},{"id":"2506.03009","title":"Conditioning Large Language Models on Legal Systems? Detecting Punishable Hate Speech","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2506.10093","title":"Leveraging LLMs for Mission Planning in Precision Agriculture","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2507.18442","title":"AraTable: Benchmarking LLMs' Reasoning and Understanding of Arabic Tabular Data","created":"2025-07-24","cited_by_count":2,"area":"lr"},{"id":"2508.15910","title":"Evaluating Structured Decoding for Text-to-Table Generation: Evidence from Three Datasets","created":"2025-08-21","cited_by_count":2,"area":null},{"id":"2510.00276","title":"SafePassage: High-Fidelity Information Extraction with Black Box LLMs","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2510.09211","title":"DICE: Structured Reasoning in LLMs through SLM-Guided Chain-of-Thought Correction","created":"2025-10-10","cited_by_count":2,"area":"lr"},{"id":"2512.14805","title":"Sharing State Between Prompts and Programs","created":"2025-12-16","cited_by_count":2,"area":null},{"id":"2601.09152","title":"PrivacyReasoner: Can LLM Emulate a Human-like Privacy Mind?","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2605.26596","title":"AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents","created":"2026-05-26","cited_by_count":2,"area":"agents"},{"id":"2606.08572","title":"OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning","created":"2026-06-07","cited_by_count":2,"area":null},{"id":"2607.00911","title":"From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained","created":"2026-07-01","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":"2507.01810","title":"Evaluating Structured Output Robustness of Small Language Models for Open Attribute-Value Extraction from Clinical Notes","created":"2025-07-02","cited_by_count":1,"area":null},{"id":"2507.04623","title":"Hierarchical Intent-guided Optimization with Pluggable LLM-Driven Semantics for Session-based Recommendation","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2510.14885","title":"You May Speak Freely: Improving the Fine-Grained Visual Recognition Capabilities of Multimodal Large Language Models with Answer Extraction","created":"2025-10-16","cited_by_count":1,"area":"mllm"},{"id":"2511.22854","title":"CRAwDAD: Causal Reasoning Augmentation with Dual-Agent Debate","created":"2025-11-28","cited_by_count":1,"area":"lr"},{"id":"2601.22035","title":"Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.06384","title":"FMBench: Adaptive Large Language Model Output Formatting","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2602.08872","title":"Large Language Models for Geolocation Extraction in Humanitarian Crisis Response","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2602.16481","title":"Leveraging Large Language Models for Causal Discovery: a Constraint-based, Argumentation-driven Approach","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2604.08851","title":"Cross-Lingual Attention Distillation with Personality-Informed Generative Augmentation for Multilingual Personality Recognition","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2604.19857","title":"Rethinking Reinforcement Fine-Tuning in LVLM: Convergence, Reward Decomposition, and Generalization","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2606.09844","title":"The Interlocutor Effect: Why LLMs Leak More Personal Data to Agents Than Humans","created":"2026-04-26","cited_by_count":1,"area":"agents"},{"id":"2606.19602","title":"Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why","created":"2026-06-17","cited_by_count":1,"area":"rag"},{"id":"2409.15076","title":"Enhancing Scientific Reproducibility Through Automated BioCompute Object Creation Using Retrieval-Augmented Generation from Publications","created":"2024-09-23","cited_by_count":0,"area":"rag"},{"id":"2410.17950","title":"Benchmarking Floworks against OpenAI & Anthropic: A Novel Framework for Enhanced LLM Function Calling","created":"2024-10-23","cited_by_count":0,"area":"agents"},{"id":"2506.13188","title":"SPOT: Bridging Natural Language and Geospatial Search for Investigative Journalists","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2508.16850","title":"RADAR: A Reasoning-Guided Attribution Framework for Explainable Visual Data Analysis","created":"2025-08-23","cited_by_count":0,"area":"lr"},{"id":"2509.12866","title":"Leveraging Large Language Models to Effectively Generate Visual Data for Canine Musculoskeletal Diagnoses","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.21862","title":"Shachi: A Modular, Controllable Framework for LLM-Based Agent-Based Modeling of Emergent Collective Behavior","created":"2025-09-26","cited_by_count":0,"area":"agents"},{"id":"2510.07516","title":"CompassLLM: A Multi-Agent Approach toward Geo-Spatial Reasoning for Popular Path Query","created":"2025-10-08","cited_by_count":0,"area":"lr"},{"id":"2511.18335","title":"OmniStruct: Universal Text-to-Structure Generation across Diverse Schemas","created":"2025-11-23","cited_by_count":0,"area":"agents"},{"id":"2512.00039","title":"LM4Opt-RA: A Multi-Candidate LLM Framework with Structured Ranking for Automating Network Resource Allocation","created":"2025-11-13","cited_by_count":0,"area":"lr"},{"id":"2601.10101","title":"Matrix as Plan: Structured Logical Reasoning with Feedback-Driven Replanning","created":"2026-01-15","cited_by_count":0,"area":"lr"},{"id":"2603.01243","title":"Suffix-Constrained Greedy Search Algorithms for Causal Language Models","created":"2026-03-01","cited_by_count":0,"area":null},{"id":"2606.09004","title":"LATTEArena: An Evaluation Framework for LLM-powered Tabular Feature Engineering (Extended Version)","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.00601","title":"\"Don't Say It!\": Constraints, Compliance, and Communication when Language Models Play Taboo","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.22683","title":"Imprompt: A Language Framework for Prompt Programming","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.24651","title":"Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels","created":"2026-07-27","cited_by_count":0,"area":"mllm"},{"id":"2608.01598","title":"PICTURE: Enhancing Theory-of-Mind in Large Language Models by Revealing, Not Hiding, Characters' Lack of Knowledge","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.18409","title":"Improving Natural-Language Combinatorial-Optimization Accuracy in Resource-Constrained Language Models via Formal Abstractions","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.22229","title":"Grounded Normative Rule Generation with Structured Search","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.22249","title":"A Tutorial on Prompt Engineering: From Messy Thoughts to AI Workflows","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.27822","title":"What Confidence Routing Is Actually Doing: Auditing Routing, Calibration, and Commitment in Multi-Agent Deliberation","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.33691","title":"When Do Agents Help? Embedding, LLM and Agentic Alignment of Classical Texts and Their Translations","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.39869","title":"GrammarRL: Effective Grammar-Constrained Decoding via Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"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":"2610.05094","title":"How Much Do LLM-as-a-Judge Design Choices Matter? A Systematic Comparison of Prompt Designs, Rating Scales, and Models","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.13287","title":"Do Prompt Optimizers Break Requirements They Are Not Scored On? A Preregistered Study","created":"2026-10-09","cited_by_count":0,"area":null},{"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":"2610.16516","title":"Intent-Triggered Anchoring for Multi-Token Format Units in Parallel Decoding of Diffusion Language Models","created":"2026-10-12","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}