{"total":65,"rows":[{"id":"2504.20595","title":"ReasonIR: Training Retrievers for Reasoning Tasks","created":"2025-04-29","cited_by_count":77,"area":"lr"},{"id":"2510.21618","title":"DeepAgent: A General Reasoning Agent with Scalable Toolsets","created":"2025-10-24","cited_by_count":71,"area":"lr"},{"id":"2404.06347","title":"RAR-b: Reasoning as Retrieval Benchmark","created":"2024-04-09","cited_by_count":36,"area":"lr"},{"id":"2511.02805","title":"MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning","created":"2025-11-04","cited_by_count":27,"area":"lr"},{"id":"2505.09970","title":"Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents","created":"2025-05-15","cited_by_count":24,"area":"lr"},{"id":"2505.23794","title":"R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning","created":"2025-05-26","cited_by_count":20,"area":"lr"},{"id":"2405.09822","title":"SEEK: Semantic Reasoning for Object Goal Navigation in Real World Inspection Tasks","created":"2024-05-16","cited_by_count":19,"area":"lr"},{"id":"2311.09821","title":"Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning","created":"2023-11-16","cited_by_count":18,"area":"lr"},{"id":"2407.01964","title":"Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction","created":"2024-07-02","cited_by_count":17,"area":"lr"},{"id":"2502.07555","title":"O1 Embedder: Let Retrievers Think Before Action","created":"2025-02-11","cited_by_count":15,"area":"lr"},{"id":"2603.01455","title":"From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents","created":"2026-03-02","cited_by_count":15,"area":"lr"},{"id":"2511.22645","title":"GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes","created":"2025-11-27","cited_by_count":14,"area":"lr"},{"id":"2412.08519","title":"Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation","created":"2024-12-11","cited_by_count":13,"area":"lr"},{"id":"2501.18724","title":"Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction","created":"2025-01-30","cited_by_count":12,"area":"lr"},{"id":"2604.02073","title":"PLUME: Latent Reasoning Based Universal Multimodal Embedding","created":"2026-04-02","cited_by_count":11,"area":"lr"},{"id":"2412.08054","title":"Federated In-Context LLM Agent Learning","created":"2024-12-11","cited_by_count":10,"area":"lr"},{"id":"2407.03061","title":"ALTER: Augmentation for Large-Table-Based Reasoning","created":"2024-07-03","cited_by_count":9,"area":"lr"},{"id":"2603.01425","title":"LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval","created":"2026-03-02","cited_by_count":9,"area":"lr"},{"id":"2508.07342","title":"PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization","created":"2025-08-10","cited_by_count":8,"area":"lr"},{"id":"2509.24869","title":"Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2510.04506","title":"GRACE: Generative Representation Learning via Contrastive Policy Optimization","created":"2025-10-06","cited_by_count":7,"area":"lr"},{"id":"2511.05549","title":"AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMs","created":"2025-11-02","cited_by_count":7,"area":"lr"},{"id":"2502.14767","title":"Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative Analysis","created":"2025-02-20","cited_by_count":6,"area":"lr"},{"id":"2502.14932","title":"Learning to Retrieve and Reason on Knowledge Graph through Active Self-Reflection","created":"2025-02-20","cited_by_count":6,"area":"lr"},{"id":"2604.12812","title":"DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding","created":"2026-04-14","cited_by_count":6,"area":"lr"},{"id":"2608.26105","title":"VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning","created":"2026-08-26","cited_by_count":6,"area":"lr"},{"id":"2502.17166","title":"JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoning","created":"2025-02-24","cited_by_count":5,"area":"lr"},{"id":"2412.02588","title":"Explainable CTR Prediction via LLM Reasoning","created":"2024-12-03","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":"2601.07054","title":"Fine-Tuning vs. RAG for Multi-Hop Question Answering with Novel Knowledge","created":"2026-01-11","cited_by_count":4,"area":"lr"},{"id":"2602.12056","title":"LawThinker: A Deep Research Legal Agent in Dynamic Environments","created":"2026-02-12","cited_by_count":4,"area":"lr"},{"id":"2604.13731","title":"Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA","created":"2026-04-15","cited_by_count":4,"area":"lr"},{"id":"2605.07153","title":"Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"id":"2607.00924","title":"Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination","created":"2026-07-01","cited_by_count":4,"area":"lr"},{"id":"2505.10870","title":"Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate","created":"2025-05-16","cited_by_count":3,"area":"lr"},{"id":"2510.26322","title":"SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Calling","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2601.17755","title":"HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG","created":"2026-01-25","cited_by_count":3,"area":"lr"},{"id":"2401.04319","title":"Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs","created":"2024-01-09","cited_by_count":2,"area":"lr"},{"id":"2504.04042","title":"An Explicit Syllogistic Legal Reasoning Framework for Large Language Models","created":"2025-04-05","cited_by_count":2,"area":"lr"},{"id":"2507.23541","title":"Med-R$^3$: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learning","created":"2025-07-31","cited_by_count":2,"area":"lr"},{"id":"2511.13726","title":"Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning","created":"2025-10-14","cited_by_count":2,"area":"lr"},{"id":"2601.05549","title":"Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval","created":"2026-01-09","cited_by_count":2,"area":"lr"},{"id":"2601.09402","title":"SEEK: Steering LLM Reasoning for RAG via Internal Reasoning Sketches","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2602.12143","title":"STAR : Bridging Statistical and Agentic Reasoning for Large Model Performance Prediction","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2603.03417","title":"Parallel Test-Time Scaling with Multi-Sequence Verifiers","created":"2026-03-03","cited_by_count":2,"area":"lr"},{"id":"2603.14006","title":"Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge Graphs","created":"2026-03-14","cited_by_count":2,"area":"lr"},{"id":"2606.16316","title":"RL-Index: Reinforcement Learning for Retrieval Index Reasoning","created":"2026-06-15","cited_by_count":2,"area":"lr"},{"id":"2404.02474","title":"uTeBC-NLP at SemEval-2024 Task 9: Can LLMs be Lateral Thinkers?","created":"2024-04-03","cited_by_count":1,"area":"lr"},{"id":"2507.02256","title":"Uncertainty-aware Reward Design Process","created":"2025-07-03","cited_by_count":1,"area":"lr"},{"id":"2509.19203","title":"Vision-Free Retrieval: Rethinking Multimodal Search with Textual Scene Descriptions","created":"2025-09-23","cited_by_count":1,"area":"lr"},{"id":"2509.20077","title":"Queryable 3D Scene Representation: A Multi-Modal Framework for Semantic Reasoning and Robotic Task Planning","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2512.11277","title":"When Actions Teach You to Think: Reasoning-Action Synergy via Reinforcement Learning in Conversational Agents","created":"2025-12-12","cited_by_count":1,"area":"lr"},{"id":"2603.10143","title":"Reason and Verify: A Framework for Faithful Retrieval-Augmented Generation","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2605.11461","title":"Breaking $\\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2610.14474","title":"RES-MR: Risk-Aware Reasoning for Explainable and Safe Medication Recommendation","created":"2026-10-10","cited_by_count":1,"area":"lr"},{"id":"2508.04032","title":"Enhancing Serendipity Recommendation System by Constructing Dynamic User Knowledge Graphs with Large Language Models","created":"2025-08-06","cited_by_count":0,"area":"lr"},{"id":"2601.21208","title":"When should I search more: Adaptive Complex Query Optimization with Reinforcement Learning","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2604.19488","title":"CoDA: Towards Effective Cross-domain Knowledge Transfer via CoT-guided Domain Adaptation","created":"2026-04-21","cited_by_count":0,"area":"lr"},{"id":"2604.25122","title":"M$^3$-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering","created":"2026-04-28","cited_by_count":0,"area":"lr"},{"id":"2606.24937","title":"The Hitchhiker's Guide to Agentic AI: From Foundations to Systems","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2607.08409","title":"When Synthetic Speech Is All You Have: Better Call GRPO","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2607.27652","title":"Harness-G: A Graph-Structured Harness for Search Agents","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2608.13200","title":"GEM: A Generative Embedding Model Bridging Reasoning and Retrieval","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2609.01658","title":"PRO-Step: Step-level Process Reward Optimization for Retrieval-Augmented Generation","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2610.11765","title":"Thinking Inertia: LLMs Keep Thinking When Told Not To","created":"2026-10-08","cited_by_count":0,"area":"lr"}],"next_cursor":null}