{"total":123,"rows":[{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557,"area":"synth"},{"id":"2402.07927","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","created":"2024-02-05","cited_by_count":431,"area":"mllm"},{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159,"area":"lr"},{"id":"2405.07437","title":"Evaluation of Retrieval-Augmented Generation: A Survey","created":"2024-05-13","cited_by_count":146,"area":"rag"},{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124,"area":null},{"id":"2402.14903","title":"Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs","created":"2024-02-22","cited_by_count":115,"area":null},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2402.18563","title":"Approaching Human-Level Forecasting with Language Models","created":"2024-02-28","cited_by_count":107,"area":null},{"id":"2311.11829","title":"System 2 Attention (is something you might need too)","created":"2023-11-20","cited_by_count":89,"area":null},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70,"area":null},{"id":"2405.19716","title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","created":"2024-05-30","cited_by_count":70,"area":"mllm"},{"id":"2409.15254","title":"Archon: An Architecture Search Framework for Inference-Time Techniques","created":"2024-09-23","cited_by_count":60,"area":null},{"id":"2409.00608","title":"TinyAgent: Function Calling at the Edge","created":"2024-09-01","cited_by_count":58,"area":"agents"},{"id":"2405.12063","title":"CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models","created":"2024-05-20","cited_by_count":54,"area":null},{"id":"2503.19213","title":"A Survey of Large Language Model Agents for Question Answering","created":"2025-03-24","cited_by_count":48,"area":"agents"},{"id":"2402.12563","title":"Confidence Matters: Revisiting Intrinsic Self-Correction Capabilities of Large Language Models","created":"2024-02-19","cited_by_count":47,"area":null},{"id":"2410.10630","title":"Thinking LLMs: General Instruction Following with Thought Generation","created":"2024-10-14","cited_by_count":45,"area":"lr"},{"id":"2501.11223","title":"Reasoning Language Models: A Blueprint","created":"2025-01-20","cited_by_count":42,"area":"lr"},{"id":"2403.19114","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","created":"2024-03-28","cited_by_count":40,"area":null},{"id":"2502.18001","title":"Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning","created":"2025-02-25","cited_by_count":40,"area":"lr"},{"id":"2402.03271","title":"Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models","created":"2024-02-05","cited_by_count":39,"area":"lr"},{"id":"2502.06855","title":"Self-Supervised Prompt Optimization","created":"2025-02-07","cited_by_count":37,"area":"lr"},{"id":"2410.06458","title":"LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints","created":"2024-10-09","cited_by_count":35,"area":"lr"},{"id":"2412.04692","title":"Smoothie: Label Free Language Model Routing","created":"2024-12-06","cited_by_count":31,"area":null},{"id":"2410.14826","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","created":"2024-10-18","cited_by_count":29,"area":null},{"id":"2412.08819","title":"HARP: A challenging human-annotated math reasoning benchmark","created":"2024-12-11","cited_by_count":27,"area":"lr"},{"id":"2506.08295","title":"From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?","created":"2025-06-09","cited_by_count":23,"area":"lr"},{"id":"2402.19248","title":"Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark","created":"2024-02-29","cited_by_count":22,"area":null},{"id":"2410.15576","title":"A Survey of Conversational Search","created":"2024-10-21","cited_by_count":22,"area":null},{"id":"2412.15238","title":"Dipper: Diversity in Prompts for Producing Large Language Model Ensembles in Reasoning tasks","created":"2024-12-12","cited_by_count":22,"area":"lr"},{"id":"2603.13285","title":"Brittlebench: Quantifying LLM robustness via prompt sensitivity","created":"2026-02-27","cited_by_count":21,"area":null},{"id":"2504.14891","title":"Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey","created":"2025-04-21","cited_by_count":20,"area":"rag"},{"id":"2406.04331","title":"PaCE: Parsimonious Concept Engineering for Large Language Models","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2502.11027","title":"On the Effect of Sampling Diversity in Scaling LLM Inference","created":"2025-02-16","cited_by_count":18,"area":null},{"id":"2312.11441","title":"Social Learning: Towards Collaborative Learning with Large Language Models","created":"2023-12-18","cited_by_count":15,"area":null},{"id":"2405.13907","title":"Just rephrase it! Uncertainty estimation in closed-source language models via multiple rephrased queries","created":"2024-05-22","cited_by_count":15,"area":null},{"id":"2406.11736","title":"Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models","created":"2024-06-17","cited_by_count":14,"area":"synth"},{"id":"2402.03099","title":"Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary cases","created":"2024-02-05","cited_by_count":13,"area":null},{"id":"2412.20372","title":"LLM2: Let Large Language Models Harness System 2 Reasoning","created":"2024-12-29","cited_by_count":12,"area":"lr"},{"id":"2402.15729","title":"How Do Humans Write Code? Large Models Do It the Same Way Too","created":"2024-02-24","cited_by_count":11,"area":"lr"},{"id":"2502.03824","title":"Syntriever: How to Train Your Retriever with Synthetic Data from LLMs","created":"2025-02-06","cited_by_count":11,"area":"synth"},{"id":"2506.06842","title":"PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media Disinformation","created":"2025-06-07","cited_by_count":11,"area":null},{"id":"2312.10321","title":"LLM-SQL-Solver: Can LLMs Determine SQL Equivalence?","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2402.08005","title":"Refined Direct Preference Optimization with Synthetic Data for Behavioral Alignment of LLMs","created":"2024-02-12","cited_by_count":10,"area":"alignment"},{"id":"2405.20252","title":"Towards Hierarchical Multi-Agent Workflows for Zero-Shot Prompt Optimization","created":"2024-05-30","cited_by_count":10,"area":"agents"},{"id":"2504.09402","title":"Read Before You Think: Mitigating LLM Comprehension Failures with Step-by-Step Reading","created":"2025-04-13","cited_by_count":10,"area":"lr"},{"id":"2503.01163","title":"Bandit-Based Prompt Design Strategy Selection Improves Prompt Optimizers","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2406.07188","title":"Merging Improves Self-Critique Against Jailbreak Attacks","created":"2024-06-11","cited_by_count":8,"area":"safety"},{"id":"2505.22990","title":"MenTeR: A fully-automated Multi-agenT workflow for end-to-end RF/Analog Circuits Netlist Design","created":"2025-05-29","cited_by_count":7,"area":null},{"id":"2402.17097","title":"Re-Ex: Revising after Explanation Reduces the Factual Errors in LLM Responses","created":"2024-02-27","cited_by_count":6,"area":null},{"id":"2404.07960","title":"Content Knowledge Identification with Multi-Agent Large Language Models (LLMs)","created":"2024-03-22","cited_by_count":6,"area":"agents"},{"id":"2502.17259","title":"Detecting Benchmark Contamination Through Watermarking","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2503.23243","title":"Evaluating how LLM annotations represent diverse views on contentious topics","created":"2025-03-29","cited_by_count":6,"area":null},{"id":"2602.03429","title":"DiscoverLLM: From Executing Intents to Discovering Them","created":"2026-02-03","cited_by_count":6,"area":null},{"id":"2604.25444","title":"One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement","created":"2026-04-28","cited_by_count":6,"area":"lr"},{"id":"2503.23913","title":"Entropy-Based Adaptive Weighting for Self-Training","created":"2025-03-31","cited_by_count":5,"area":"lr"},{"id":"2603.21520","title":"Generalizable Self-Evolving Memory for Automatic Prompt Optimization","created":"2026-03-23","cited_by_count":5,"area":"synth"},{"id":"2401.11725","title":"Speak It Out: Solving Symbol-Related Problems with Symbol-to-Language Conversion for Language Models","created":"2024-01-22","cited_by_count":4,"area":null},{"id":"2407.12529","title":"Crafting the Path: Robust Query Rewriting for Information Retrieval","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2409.06241","title":"DiPT: Enhancing LLM reasoning through diversified perspective-taking","created":"2024-09-10","cited_by_count":4,"area":"lr"},{"id":"2412.05127","title":"The Prompt Canvas: A Literature-Based Practitioner Guide for Creating Effective Prompts in Large Language Models","created":"2024-12-06","cited_by_count":4,"area":null},{"id":"2412.21006","title":"Verbosity-Aware Rationale Reduction: Effective Reduction of Redundant Rationale via Principled Criteria","created":"2024-12-30","cited_by_count":4,"area":null},{"id":"2501.03508","title":"A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Models","created":"2025-01-07","cited_by_count":4,"area":null},{"id":"2506.18102","title":"InspireDebate: Multi-Dimensional Subjective-Objective Evaluation-Guided Reasoning and Optimization for Debating","created":"2025-06-22","cited_by_count":4,"area":"lr"},{"id":"2510.06652","title":"Aligning Large Language Models via Fully Self-Synthetic Data","created":"2025-10-08","cited_by_count":4,"area":"alignment"},{"id":"2511.21568","title":"RoParQ: Paraphrase-Aware Alignment of Large Language Models Towards Robustness to Paraphrased Questions","created":"2025-11-26","cited_by_count":4,"area":"alignment"},{"id":"2407.21227","title":"TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2411.05281","title":"Fox-1: Open Small Language Model for Cloud and Edge","created":"2024-11-08","cited_by_count":3,"area":null},{"id":"2501.13333","title":"AgentRec: Agent Recommendation Using Sentence Embeddings Aligned to Human Feedback","created":"2025-01-23","cited_by_count":3,"area":"agents"},{"id":"2502.09974","title":"Has My System Prompt Been Used? Large Language Model Prompt Membership Inference","created":"2025-02-14","cited_by_count":3,"area":"safety"},{"id":"2505.16307","title":"PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Models","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2506.02480","title":"ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2507.07307","title":"Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation","created":"2025-07-09","cited_by_count":3,"area":"rag"},{"id":"2510.25441","title":"Grounded in Reality: Learning and Deploying Proactive LLM from Offline Logs","created":"2025-10-29","cited_by_count":3,"area":null},{"id":"2512.02841","title":"Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2402.10645","title":"Can Separators Improve Chain-of-Thought Prompting?","created":"2024-02-16","cited_by_count":2,"area":"lr"},{"id":"2506.07135","title":"Taxonomy of migration scenarios for Qiskit refactoring using LLMs","created":"2025-06-08","cited_by_count":2,"area":null},{"id":"2506.11561","title":"Identifying Helpful Context for LLM-based Vulnerability Repair: A Preliminary Study","created":"2025-06-13","cited_by_count":2,"area":null},{"id":"2506.11989","title":"Thought Graph Traversal for Test-time Scaling in Chest X-ray VLLMs","created":"2025-06-13","cited_by_count":2,"area":"lr"},{"id":"2507.21693","title":"MultiAIGCD: A Comprehensive dataset for AI Generated Code Detection Covering Multiple Languages, Models,Prompts, and Scenarios","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2508.08308","title":"First Ask Then Answer: A Framework Design for AI Dialogue Based on Supplementary Questioning with Large Language Models","created":"2025-08-08","cited_by_count":2,"area":null},{"id":"2508.11975","title":"Chart-CoCa: Self-Improving Chart Understanding of Vision LMs via Code-Driven Synthesis and Candidate-Conditioned Answering","created":"2025-08-16","cited_by_count":2,"area":"mllm"},{"id":"2510.03223","title":"Attention-Aligned Reasoning for Large Language Models","created":"2025-10-03","cited_by_count":2,"area":"lr"},{"id":"2511.14772","title":"Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2605.24432","title":"Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2401.08772","title":"HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2404.18371","title":"QANA: LLM-based Question Generation and Network Analysis for Zero-shot Key Point Analysis and Beyond","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2408.09365","title":"Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting","created":"2024-08-18","cited_by_count":1,"area":null},{"id":"2502.09390","title":"SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models","created":"2025-02-13","cited_by_count":1,"area":"lr"},{"id":"2506.14535","title":"Automatic Qiskit Code Refactoring Using Large Language Models","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2507.08621","title":"A comprehensive study of LLM-based argument classification: from LLAMA through GPT-4o to Deepseek-R1","created":"2025-07-11","cited_by_count":1,"area":"lr"},{"id":"2507.19756","title":"Are You There God? Lightweight Narrative Annotation of Christian Fiction with LMs","created":"2025-07-26","cited_by_count":1,"area":null},{"id":"2508.10019","title":"Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2508.16697","title":"QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting","created":"2025-08-22","cited_by_count":1,"area":"lr"},{"id":"2509.19593","title":"GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Models","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2601.03359","title":"Enhancing LLM Instruction Following: An Evaluation-Driven Multi-Agentic Workflow for Prompt Instructions Optimization","created":"2026-01-06","cited_by_count":1,"area":"agents"},{"id":"2601.23273","title":"UPA: Unsupervised Prompt Agent via Tree-Based Search and Selection","created":"2026-01-30","cited_by_count":1,"area":"agents"},{"id":"2603.19253","title":"A comprehensive study of LLM-based argument classification: from Llama through DeepSeek to GPT-5.2","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2604.17105","title":"How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2604.19771","title":"Cognis: Context-Aware Memory for Conversational AI Agents","created":"2026-03-27","cited_by_count":1,"area":"agents"}],"next_cursor":"100"}