{"total":150,"rows":[{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212,"area":"lr"},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479,"area":"lr"},{"id":"2210.11610","title":"Large Language Models Can Self-Improve","created":"2022-10-20","cited_by_count":664,"area":"lr"},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529,"area":"lr"},{"id":"2310.02226","title":"Think before you speak: Training Language Models With Pause Tokens","created":"2023-10-03","cited_by_count":264,"area":"lr"},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246,"area":"lr"},{"id":"2406.10149","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","created":"2024-06-14","cited_by_count":215,"area":"lr"},{"id":"2210.03849","title":"ConvFinQA: Exploring the Chain of Numerical Reasoning in Conversational Finance Question Answering","created":"2022-10-07","cited_by_count":196,"area":"lr"},{"id":"2301.00303","title":"Rethinking with Retrieval: Faithful Large Language Model Inference","created":"2022-12-31","cited_by_count":145,"area":"lr"},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"id":"2512.08296","title":"Towards a Science of Scaling Agent Systems","created":"2025-12-09","cited_by_count":138,"area":"lr"},{"id":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"id":"2503.15850","title":"Uncertainty Quantification and Confidence Calibration in Large Language Models: A Survey","created":"2025-03-20","cited_by_count":95,"area":"lr"},{"id":"2205.11502","title":"On the Paradox of Learning to Reason from Data","created":"2022-05-23","cited_by_count":93,"area":"lr"},{"id":"2504.20595","title":"ReasonIR: Training Retrievers for Reasoning Tasks","created":"2025-04-29","cited_by_count":77,"area":"lr"},{"id":"2304.04812","title":"Scallop: A Language for Neurosymbolic Programming","created":"2023-04-10","cited_by_count":63,"area":"lr"},{"id":"2510.23595","title":"Multi-Agent Evolve: LLM Self-Improve through Co-evolution","created":"2025-10-27","cited_by_count":60,"area":"lr"},{"id":"2303.00293","title":"How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks","created":"2023-03-01","cited_by_count":58,"area":"lr"},{"id":"2509.25911","title":"Mem-{\\alpha}: Learning Memory Construction via Reinforcement Learning","created":"2025-09-30","cited_by_count":55,"area":"lr"},{"id":"2501.14342","title":"Chain-of-Retrieval Augmented Generation","created":"2025-01-24","cited_by_count":49,"area":"lr"},{"id":"2201.11473","title":"Reasoning Like Program Executors","created":"2022-01-27","cited_by_count":45,"area":"lr"},{"id":"2602.15902","title":"Doc-to-LoRA: Learning to Instantly Internalize Contexts","created":"2026-02-13","cited_by_count":43,"area":"lr"},{"id":"2310.00835","title":"TRAM: Benchmarking Temporal Reasoning for Large Language Models","created":"2023-10-02","cited_by_count":40,"area":"lr"},{"id":"2306.08952","title":"Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models","created":"2023-06-15","cited_by_count":37,"area":"lr"},{"id":"2410.20482","title":"What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration","created":"2024-10-27","cited_by_count":31,"area":"lr"},{"id":"2507.02092","title":"Energy-Based Transformers are Scalable Learners and Thinkers","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2402.11924","title":"Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark","created":"2024-02-19","cited_by_count":27,"area":"lr"},{"id":"2410.03227","title":"ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering","created":"2024-10-04","cited_by_count":26,"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":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2409.13035","title":"TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning","created":"2024-09-19","cited_by_count":22,"area":"lr"},{"id":"2211.05588","title":"Watching the News: Towards VideoQA Models that can Read","created":"2022-11-10","cited_by_count":20,"area":"lr"},{"id":"2502.12130","title":"Scaling Autonomous Agents via Automatic Reward Modeling And Planning","created":"2025-02-17","cited_by_count":19,"area":"lr"},{"id":"2412.15176","title":"Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure","created":"2024-12-19","cited_by_count":18,"area":"lr"},{"id":"2502.15845","title":"Verify when Uncertain: Beyond Self-Consistency in Black Box Hallucination Detection","created":"2025-02-20","cited_by_count":18,"area":"lr"},{"id":"2508.13250","title":"Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information","created":"2025-08-18","cited_by_count":17,"area":"lr"},{"id":"2409.02257","title":"MMLU-Pro+: Evaluating Higher-Order Reasoning and Shortcut Learning in LLMs","created":"2024-09-03","cited_by_count":16,"area":"lr"},{"id":"2209.14901","title":"DR.BENCH: Diagnostic Reasoning Benchmark for Clinical Natural Language Processing","created":"2022-09-29","cited_by_count":14,"area":"lr"},{"id":"2210.10105","title":"ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler","created":"2022-10-18","cited_by_count":14,"area":"lr"},{"id":"2502.20377","title":"PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation","created":"2025-02-27","cited_by_count":14,"area":"lr"},{"id":"2204.07408","title":"Towards Fine-grained Causal Reasoning and QA","created":"2022-04-15","cited_by_count":13,"area":"lr"},{"id":"2407.03181","title":"Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs","created":"2024-07-03","cited_by_count":12,"area":"lr"},{"id":"2205.08794","title":"LogiGAN: Learning Logical Reasoning via Adversarial Pre-training","created":"2022-05-18","cited_by_count":11,"area":"lr"},{"id":"2305.12599","title":"Abstract Meaning Representation-Based Logic-Driven Data Augmentation for Logical Reasoning","created":"2023-05-21","cited_by_count":11,"area":"lr"},{"id":"2310.01290","title":"Knowledge Crosswords: Geometric Knowledge Reasoning with Large Language Models","created":"2023-10-02","cited_by_count":11,"area":"lr"},{"id":"2310.14709","title":"Once Upon a $\\textit{Time}$ in $\\textit{Graph}$: Relative-Time Pretraining for Complex Temporal Reasoning","created":"2023-10-23","cited_by_count":11,"area":"lr"},{"id":"2503.10061","title":"Compute Optimal Scaling of Skills: Knowledge vs Reasoning","created":"2025-03-13","cited_by_count":11,"area":"lr"},{"id":"2507.15337","title":"Reasoning Models are Test Exploiters: Rethinking Multiple-Choice","created":"2025-07-21","cited_by_count":11,"area":"lr"},{"id":"2307.09636","title":"Traffic-Domain Video Question Answering with Automatic Captioning","created":"2023-07-18","cited_by_count":10,"area":"lr"},{"id":"2402.11541","title":"Large Language Models Can Better Understand Knowledge Graphs Than We Thought","created":"2024-02-18","cited_by_count":10,"area":"lr"},{"id":"2409.00781","title":"Generating Media Background Checks for Automated Source Critical Reasoning","created":"2024-09-01","cited_by_count":10,"area":"lr"},{"id":"2204.07693","title":"Calibrating Trust of Multi-Hop Question Answering Systems with Decompositional Probes","created":"2022-04-16","cited_by_count":9,"area":"lr"},{"id":"2205.10714","title":"Interpretable Proof Generation via Iterative Backward Reasoning","created":"2022-05-22","cited_by_count":9,"area":"lr"},{"id":"2409.16909","title":"Enhancing Temporal Sensitivity and Reasoning for Time-Sensitive Question Answering","created":"2024-09-25","cited_by_count":9,"area":"lr"},{"id":"2503.02003","title":"HoT: Highlighted Chain of Thought for Referencing Supporting Facts from Inputs","created":"2025-03-03","cited_by_count":9,"area":"lr"},{"id":"2602.10560","title":"When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning","created":"2026-02-11","cited_by_count":9,"area":"lr"},{"id":"2203.08992","title":"AdaLoGN: Adaptive Logic Graph Network for Reasoning-Based Machine Reading Comprehension","created":"2022-03-16","cited_by_count":8,"area":"lr"},{"id":"2203.10557","title":"A Neural-Symbolic Approach to Natural Language Understanding","created":"2022-03-20","cited_by_count":8,"area":"lr"},{"id":"2205.00731","title":"Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning","created":"2022-05-02","cited_by_count":8,"area":"lr"},{"id":"2211.05417","title":"Can Transformers Reason in Fragments of Natural Language?","created":"2022-11-10","cited_by_count":8,"area":"lr"},{"id":"2602.18493","title":"Learning to Remember: End-to-End Training of Memory Agents for Long-Context Reasoning","created":"2026-02-13","cited_by_count":8,"area":"lr"},{"id":"2210.04234","title":"Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answering","created":"2022-10-09","cited_by_count":7,"area":"lr"},{"id":"2405.00021","title":"SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials","created":"2024-02-22","cited_by_count":7,"area":"lr"},{"id":"2410.13987","title":"RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine","created":"2024-10-17","cited_by_count":7,"area":"lr"},{"id":"2507.03928","title":"CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate","created":"2025-07-05","cited_by_count":7,"area":"lr"},{"id":"2607.26760","title":"Metis: Memory Foundation Model","created":"2026-07-29","cited_by_count":7,"area":"lr"},{"id":"2202.13529","title":"KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models","created":"2022-02-28","cited_by_count":6,"area":"lr"},{"id":"2208.10297","title":"Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering","created":"2022-08-22","cited_by_count":6,"area":"lr"},{"id":"2305.06841","title":"Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models","created":"2023-05-11","cited_by_count":6,"area":"lr"},{"id":"2402.09390","title":"HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluation","created":"2024-02-14","cited_by_count":6,"area":"lr"},{"id":"2509.03162","title":"SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhala","created":"2025-09-03","cited_by_count":6,"area":"lr"},{"id":"2305.08246","title":"Learning Non-linguistic Skills without Sacrificing Linguistic Proficiency","created":"2023-05-14","cited_by_count":5,"area":"lr"},{"id":"2309.12669","title":"HRoT: Hybrid prompt strategy and Retrieval of Thought for Table-Text Hybrid Question Answering","created":"2023-09-22","cited_by_count":5,"area":"lr"},{"id":"2402.07812","title":"Retrieval Augmented Thought Process for Private Data Handling in Healthcare","created":"2024-02-12","cited_by_count":5,"area":"lr"},{"id":"2404.11717","title":"How often are errors in natural language reasoning due to paraphrastic variability?","created":"2024-04-17","cited_by_count":5,"area":"lr"},{"id":"2504.04771","title":"Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations","created":"2025-04-07","cited_by_count":5,"area":"lr"},{"id":"2504.14858","title":"Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization","created":"2025-04-21","cited_by_count":5,"area":"lr"},{"id":"2505.16686","title":"SPaRC: A Spatial Pathfinding Reasoning Challenge","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2505.20993","title":"Who Reasons in the Large Language Models?","created":"2025-05-27","cited_by_count":5,"area":"lr"},{"id":"2205.10442","title":"Down and Across: Introducing Crossword-Solving as a New NLP Benchmark","created":"2022-05-20","cited_by_count":4,"area":"lr"},{"id":"2503.04973","title":"Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning","created":"2025-03-06","cited_by_count":4,"area":"lr"},{"id":"2505.09825","title":"KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive Reasoning","created":"2025-05-14","cited_by_count":4,"area":"lr"},{"id":"2506.05766","title":"BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2510.19358","title":"M3-SLU: Evaluating Speaker-Attributed Reasoning in Multimodal Large Language Models","created":"2025-10-22","cited_by_count":4,"area":"lr"},{"id":"2601.06022","title":"AdaFuse: Adaptive Ensemble Decoding with Test-Time Scaling for LLMs","created":"2026-01-09","cited_by_count":4,"area":"lr"},{"id":"2602.05897","title":"Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2604.06794","title":"GCoT-Decoding: Unlocking Deep Reasoning Paths for Universal Question Answering","created":"2026-04-08","cited_by_count":4,"area":"lr"},{"id":"2210.07519","title":"Can Language Representation Models Think in Bets?","created":"2022-10-14","cited_by_count":3,"area":"lr"},{"id":"2410.23511","title":"Dynamic Strategy Planning for Efficient Question Answering with Large Language Models","created":"2024-10-30","cited_by_count":3,"area":"lr"},{"id":"2508.17117","title":"PlantExpertVQA: A Visual Question Answering Dataset for Benchmarking Vision-Language Models in Plant Science","created":"2025-08-23","cited_by_count":3,"area":"lr"},{"id":"2510.20535","title":"ARC-Encoder: learning compressed text representations for large language models","created":"2025-10-23","cited_by_count":3,"area":"lr"},{"id":"2601.12465","title":"Incentivizing In-depth Reasoning over Long Contexts with Process Advantage Shaping","created":"2026-01-18","cited_by_count":3,"area":"lr"},{"id":"2603.29232","title":"Long-Document QA with Chain-of-Structured-Thought and Fine-Tuned SLMs","created":"2026-03-31","cited_by_count":3,"area":"lr"},{"id":"2605.03379","title":"Two Calls, Two Moments, and the Vote-Accuracy Curve of Repeated LLM Inference","created":"2026-05-05","cited_by_count":3,"area":"lr"},{"id":"2207.01450","title":"Discourse-Aware Graph Networks for Textual Logical Reasoning","created":"2022-07-04","cited_by_count":2,"area":"lr"},{"id":"2210.01258","title":"Understanding Prior Bias and Choice Paralysis in Transformer-based Language Representation Models through Four Experimental Probes","created":"2022-10-03","cited_by_count":2,"area":"lr"},{"id":"2301.02983","title":"Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text","created":"2023-01-08","cited_by_count":2,"area":"lr"},{"id":"2305.14569","title":"Few-shot Unified Question Answering: Tuning Models or Prompts?","created":"2023-05-23","cited_by_count":2,"area":"lr"},{"id":"2305.14682","title":"TACR: A Table-alignment-based Cell-selection and Reasoning Model for Hybrid Question-Answering","created":"2023-05-24","cited_by_count":2,"area":"lr"},{"id":"2311.04659","title":"Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models","created":"2023-11-08","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}