{"list":"other","total":51,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"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":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"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":"2602.02276","title":"Kimi K2.5: Visual Agentic Intelligence","created":"2026-02-02","cited_by_count":501},{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497},{"id":"2209.00840","title":"FOLIO: Natural Language Reasoning with First-Order Logic","created":"2022-09-02","cited_by_count":235},{"id":"2409.00920","title":"ToolACE: Winning the Points of LLM Function Calling","created":"2024-09-02","cited_by_count":216},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208},{"id":"2312.14852","title":"TACO: Topics in Algorithmic COde generation dataset","created":"2023-12-22","cited_by_count":160},{"id":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","cited_by_count":125},{"id":"2409.19886","title":"RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models","created":"2024-09-30","cited_by_count":88},{"id":"2509.21240","title":"Tree Search for LLM Agent Reinforcement Learning","created":"2025-09-25","cited_by_count":79},{"id":"2506.09033","title":"Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning","created":"2025-06-10","cited_by_count":72},{"id":"2511.21689","title":"ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration","created":"2025-11-26","cited_by_count":47},{"id":"2601.07206","title":"LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing","created":"2026-01-12","cited_by_count":38},{"id":"2512.08153","title":"TreeGRPO: Tree-Advantage GRPO for Online RL Post-Training of Diffusion Models","created":"2025-12-09","cited_by_count":31},{"id":"2510.09719","title":"ICL-Router: In-Context Learned Model Representations for LLM Routing","created":"2025-10-10","cited_by_count":28},{"id":"2405.17402","title":"THREAD: Thinking Deeper with Recursive Spawning","created":"2024-05-27","cited_by_count":25},{"id":"2602.19672","title":"SkillOrchestra: Learning to Route Agents via Skill Transfer","created":"2026-02-23","cited_by_count":23},{"id":"2601.13671","title":"The Orchestration of Multi-Agent Systems: Architectures, Protocols, and Enterprise Adoption","created":"2026-01-20","cited_by_count":15},{"id":"2506.05901","title":"Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router","created":"2025-06-06","cited_by_count":13},{"id":"2604.09377","title":"Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios","created":"2026-04-10","cited_by_count":10},{"id":"2601.09692","title":"Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection","created":"2026-01-14","cited_by_count":4},{"id":"2602.10622","title":"How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning","created":"2026-02-11","cited_by_count":3},{"id":"2604.16401","title":"GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning","created":"2026-03-31","cited_by_count":1}],"next_cursor":null}