{"list":"other","total":51,"rows":[{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810},{"id":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2507.18071","title":"Group Sequence Policy Optimization","created":"2025-07-24","cited_by_count":835},{"id":"1801.07243","title":"Personalizing Dialogue Agents: I have a dog, do you have pets too?","created":"2018-01-22","cited_by_count":828},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627},{"id":"2304.11406","title":"LaMP: When Large Language Models Meet Personalization","created":"2023-04-22","cited_by_count":437},{"id":"2410.08146","title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning","created":"2024-10-10","cited_by_count":279},{"id":"1301.3836","title":"The Complexity of Decentralized Control of Markov Decision Processes","created":"2013-01-16","cited_by_count":231},{"id":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193},{"id":"2502.09597","title":"Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs","created":"2025-02-13","cited_by_count":148},{"id":"1509.08731","title":"Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning","created":"2015-09-29","cited_by_count":144},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126},{"id":"2502.00640","title":"CollabLLM: From Passive Responders to Active Collaborators","created":"2025-02-02","cited_by_count":124},{"id":"2504.16828","title":"Process Reward Models That Think","created":"2025-04-23","cited_by_count":118},{"id":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111},{"id":"2310.10080","title":"Let's reward step by step: Step-Level reward model as the Navigators for Reasoning","created":"2023-10-16","cited_by_count":102},{"id":"2406.01265","title":"The Dawn of Natural Language to SQL: Are We Fully Ready?","created":"2024-06-03","cited_by_count":79},{"id":"2507.22034","title":"UserBench: An Interactive Gym Environment for User-Centric Agents","created":"2025-07-29","cited_by_count":76},{"id":"2402.09205","title":"Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents","created":"2024-02-14","cited_by_count":74},{"id":"2504.04717","title":"Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models","created":"2025-04-07","cited_by_count":62},{"id":"2409.20296","title":"PersonalLLM: Tailoring LLMs to Individual Preferences","created":"2024-09-30","cited_by_count":60},{"id":"2406.00222","title":"Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training","created":"2024-05-31","cited_by_count":57},{"id":"2408.05109","title":"A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?","created":"2024-08-09","cited_by_count":56},{"id":"2405.07001","title":"ChartInsights: Evaluating Multimodal Large Language Models for Low-Level Chart Question Answering","created":"2024-05-11","cited_by_count":50},{"id":"2511.02208","title":"Training Proactive and Personalized LLM Agents","created":"2025-11-04","cited_by_count":46},{"id":"2602.03786","title":"AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration","created":"2026-02-03","cited_by_count":35},{"id":"2502.17248","title":"Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search","created":"2025-02-24","cited_by_count":34},{"id":"2506.00137","title":"LaMP-QA: A Benchmark for Personalized Long-form Question Answering","created":"2025-05-30","cited_by_count":31},{"id":"2510.23587","title":"A Survey of Data Agents: Emerging Paradigm or Overstated Hype?","created":"2025-10-27","cited_by_count":30},{"id":"2509.13232","title":"Single-stream Policy Optimization","created":"2025-09-16","cited_by_count":28},{"id":"2510.17586","title":"DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework","created":"2025-10-20","cited_by_count":28},{"id":"2502.11250","title":"Uncertainty-Aware Step-wise Verification with Generative Reward Models","created":"2025-02-16","cited_by_count":22},{"id":"2505.11065","title":"Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking","created":"2025-05-16","cited_by_count":21},{"id":"2602.14296","title":"AutoWebWorld: Synthesizing Infinite Verifiable Web Environments via Finite State Machines","created":"2026-02-15","cited_by_count":21},{"id":"2510.22373","title":"VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations","created":"2025-10-25","cited_by_count":16},{"id":"2505.07437","title":"LEAD: Iterative Data Selection for Efficient LLM Instruction Tuning","created":"2025-05-12","cited_by_count":13},{"id":"2510.24668","title":"InteractComp: Evaluating Search Agents With Ambiguous Queries","created":"2025-10-28","cited_by_count":12},{"id":"2510.04491","title":"Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents","created":"2025-10-06","cited_by_count":10},{"id":"2512.00499","title":"ESPO: Entropy Importance Sampling Policy Optimization","created":"2025-11-29","cited_by_count":9},{"id":"2512.13159","title":"SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning","created":"2025-12-15","cited_by_count":8},{"id":"2508.17711","title":"Enhancing LLM-Based Social Bot via an Adversarial Learning Framework","created":"2025-08-25","cited_by_count":7},{"id":"2601.03775","title":"Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations","created":"2026-01-07","cited_by_count":7},{"id":"2410.07863","title":"Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games","created":"2024-10-10","cited_by_count":6},{"id":"2412.10674","title":"USM: Unbiased Survey Modeling for Limiting Negative User Experiences in Recommendation Systems","created":"2024-12-14","cited_by_count":3}],"next_cursor":null}