{"list":"other","total":86,"rows":[{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"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":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982},{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2312.08935","title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","created":"2023-12-14","cited_by_count":928},{"id":"2212.10509","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","created":"2022-12-20","cited_by_count":923},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2506.07982","title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","created":"2025-06-09","cited_by_count":627},{"id":"2507.19457","title":"GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning","created":"2025-07-25","cited_by_count":542},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"2403.14403","title":"Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity","created":"2024-03-21","cited_by_count":451},{"id":"2504.21776","title":"WebThinker: Empowering Large Reasoning Models with Deep Research Capability","created":"2025-04-30","cited_by_count":335},{"id":"2310.03716","title":"A Long Way to Go: Investigating Length Correlations in RLHF","created":"2023-10-05","cited_by_count":291},{"id":"2406.18629","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","created":"2024-06-26","cited_by_count":273},{"id":"2410.21819","title":"Self-Preference Bias in LLM-as-a-Judge","created":"2024-10-29","cited_by_count":258},{"id":"2407.01502","title":"AI Agents That Matter","created":"2024-07-01","cited_by_count":219},{"id":"2505.10468","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","created":"2025-05-15","cited_by_count":169},{"id":"2409.12941","title":"Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation","created":"2024-09-19","cited_by_count":162},{"id":"2411.00640","title":"Adding Error Bars to Evals: A Statistical Approach to Language Model Evaluations","created":"2024-11-01","cited_by_count":148},{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145},{"id":"1907.06554","title":"Asking Clarifying Questions in Open-Domain Information-Seeking Conversations","created":"2019-07-15","cited_by_count":139},{"id":"2211.02570","title":"The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation","created":"2022-11-04","cited_by_count":139},{"id":"2403.00409","title":"Provably Robust DPO: Aligning Language Models with Noisy Feedback","created":"2024-03-01","cited_by_count":135},{"id":"2001.11770","title":"Break It Down: A Question Understanding Benchmark","created":"2020-01-31","cited_by_count":131},{"id":"1805.04655","title":"Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information","created":"2018-05-12","cited_by_count":115},{"id":"2403.19154","title":"STaR-GATE: Teaching Language Models to Ask Clarifying Questions","created":"2024-03-28","cited_by_count":104},{"id":"2507.02825","title":"Establishing Best Practices for Building Rigorous Agentic Benchmarks","created":"2025-07-03","cited_by_count":102},{"id":"2410.12361","title":"Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance","created":"2024-10-16","cited_by_count":87},{"id":"2507.10532","title":"Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination","created":"2025-07-14","cited_by_count":82},{"id":"2410.13788","title":"Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions","created":"2024-10-17","cited_by_count":76},{"id":"2507.22034","title":"UserBench: An Interactive Gym Environment for User-Centric Agents","created":"2025-07-29","cited_by_count":76},{"id":"2503.22674","title":"QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?","created":"2025-03-28","cited_by_count":63},{"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":"2511.02208","title":"Training Proactive and Personalized LLM Agents","created":"2025-11-04","cited_by_count":46},{"id":"2504.13359","title":"Cost-of-Pass: An Economic Framework for Evaluating Language Models","created":"2025-04-17","cited_by_count":35},{"id":"2510.18821","title":"Search Self-play: Pushing the Frontier of Agent Capability without Supervision","created":"2025-10-21","cited_by_count":34},{"id":"2509.19736","title":"UserRL: Training Interactive User-Centric Agent via Reinforcement Learning","created":"2025-09-24","cited_by_count":32},{"id":"2402.17497","title":"REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering","created":"2024-02-27","cited_by_count":28},{"id":"2606.19544","title":"Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias","created":"2026-06-17","cited_by_count":28},{"id":"2310.03659","title":"Balancing Autonomy and Alignment: A Multi-Dimensional Taxonomy for Autonomous LLM-powered Multi-Agent Architectures","created":"2023-10-05","cited_by_count":25},{"id":"2406.17453","title":"Learning to Ask Informative Questions: Enhancing LLMs with Preference Optimization and Expected Information Gain","created":"2024-06-25","cited_by_count":21},{"id":"2512.07850","title":"SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agents","created":"2025-11-26","cited_by_count":21},{"id":"2405.15784","title":"CLARINET: Augmenting Language Models to Ask Clarification Questions for Retrieval","created":"2024-04-28","cited_by_count":20},{"id":"2606.29957","title":"SWE-Together: Evaluating Coding Agents in Interactive User Sessions","created":"2026-06-29","cited_by_count":18},{"id":"2604.06185","title":"Benchmarking LLM Tool-Use in the Wild","created":"2026-02-13","cited_by_count":17},{"id":"2602.04482","title":"ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World Data","created":"2026-02-04","cited_by_count":16},{"id":"2602.11199","title":"When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification","created":"2026-02-04","cited_by_count":16},{"id":"2604.00842","title":"Proactive Agent Research Environment: Simulating Active Users to Evaluate Proactive Assistants","created":"2026-04-01","cited_by_count":15},{"id":"2507.21389","title":"Teaching Language Models To Gather Information Proactively","created":"2025-07-28","cited_by_count":14},{"id":"2604.17073","title":"Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL","created":"2026-04-18","cited_by_count":14},{"id":"2510.24668","title":"InteractComp: Evaluating Search Agents With Ambiguous Queries","created":"2025-10-28","cited_by_count":12},{"id":"2603.00656","title":"InfoPO: Information-Driven Policy Optimization for User-Centric Agents","created":"2026-02-28","cited_by_count":12},{"id":"2605.27141","title":"VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions","created":"2026-05-26","cited_by_count":12},{"id":"2409.06411","title":"Length Desensitization in Direct Preference Optimization","created":"2024-09-10","cited_by_count":8},{"id":"2510.14278","title":"PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering","created":"2025-10-16","cited_by_count":8},{"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":"2510.08517","title":"CaRT: Teaching LLM Agents to Know When They Know Enough","created":"2025-10-09","cited_by_count":7},{"id":"2511.19794","title":"When +1% Is Not Enough: A Paired Bootstrap Protocol for Evaluating Small Improvements","created":"2025-11-24","cited_by_count":7},{"id":"2602.03304","title":"To Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention","created":"2026-02-03","cited_by_count":7},{"id":"2604.14054","title":"$\\pi$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data","created":"2026-04-15","cited_by_count":7},{"id":"2606.13685","title":"The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation","created":"2026-04-23","cited_by_count":7},{"id":"2601.21162","title":"A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning","created":"2026-01-29","cited_by_count":6},{"id":"2603.12109","title":"On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents","created":"2026-03-12","cited_by_count":6},{"id":"2605.12975","title":"Retrieval is Cheap, Show Me the Code: Executable Multi-Hop Reasoning for Retrieval-Augmented Generation","created":"2026-05-13","cited_by_count":5},{"id":"2605.09228","title":"ProactBench: Beyond What The User Asked For","created":"2026-05-09","cited_by_count":4},{"id":"2604.17609","title":"Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity","created":"2026-04-19","cited_by_count":3},{"id":"2605.06717","title":"Agentic Coding Needs Proactivity, Not Just Autonomy","created":"2026-05-07","cited_by_count":3},{"id":"2503.02922","title":"Optimizing open-domain question answering with graph-based retrieval augmented generation","created":"2025-03-04","cited_by_count":2},{"id":"2602.11351","title":"Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization","created":"2026-02-11","cited_by_count":2},{"id":"2605.28093","title":"ConRAG: Consensus-Driven Multi-View Retrieval for Multi-Hop Question Answering","created":"2026-05-27","cited_by_count":2},{"id":"2605.28108","title":"Ask Now, Use Later: Benchmarking the Proactivity Gap in Long-Lived LLM Agents","created":"2026-05-27","cited_by_count":2},{"id":"2609.03727","title":"Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluation","created":"2026-09-03","cited_by_count":2},{"id":"2605.27882","title":"VibeSearchBench: Benchmarking Long-horizon Proactive Search in the Wild","created":"2026-05-27","cited_by_count":1},{"id":"2606.03318","title":"Beyond Ideal Instruction: A Comprehensive Framework for Evaluating LLMs in Realistic Interactions","created":"2026-06-02","cited_by_count":1},{"id":"2606.27669","title":"When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search","created":"2026-06-26","cited_by_count":1}],"next_cursor":null}