{"total":59,"rows":[{"id":"2512.08296","title":"Towards a Science of Scaling Agent Systems","created":"2025-12-09","cited_by_count":138,"area":"lr"},{"id":"2512.20848","title":"Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2025-12-23","cited_by_count":104,"area":"lr"},{"id":"2511.01824","title":"Simulating Environments with Reasoning Models for Agent Training","created":"2025-11-03","cited_by_count":57,"area":"lr"},{"id":"2511.17006","title":"Budget-Aware Tool Use Enables Effective Agent Scaling","created":"2025-11-21","cited_by_count":44,"area":"lr"},{"id":"2606.13392","title":"MiniMax Sparse Attention","created":"2026-06-11","cited_by_count":44,"area":"lr"},{"id":"2606.15007","title":"Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-06-12","cited_by_count":42,"area":"lr"},{"id":"2601.16725","title":"LongCat-Flash-Thinking-2601 Technical Report","created":"2026-01-23","cited_by_count":34,"area":"lr"},{"id":"2511.15718","title":"ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset","created":"2025-11-12","cited_by_count":30,"area":"lr"},{"id":"2508.17692","title":"LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios","created":"2025-08-25","cited_by_count":26,"area":"lr"},{"id":"2602.18998","title":"Benchmark Test-Time Scaling of General LLM Agents","created":"2026-02-22","cited_by_count":26,"area":"lr"},{"id":"2509.18883","title":"Introducing LongCat-Flash-Thinking: A Technical Report","created":"2025-09-23","cited_by_count":22,"area":"lr"},{"id":"2605.09252","title":"LLM Agents Already Know When to Call Tools -- Even Without Reasoning","created":"2026-05-10","cited_by_count":19,"area":"lr"},{"id":"2509.06733","title":"Reinforcement Learning Foundations for Deep Research Systems: A Survey","created":"2025-09-08","cited_by_count":14,"area":"lr"},{"id":"2509.25534","title":"Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning","created":"2025-09-19","cited_by_count":11,"area":"lr"},{"id":"2601.15625","title":"Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors","created":"2026-01-22","cited_by_count":10,"area":"lr"},{"id":"2607.07405","title":"Reason Less, Verify More: Deterministic Gates Recover a Silent Policy-Violation Failure Mode in Tool-Using LLM Agents","created":"2026-07-08","cited_by_count":10,"area":"lr"},{"id":"2511.01365","title":"The Ouroboros of Benchmarking: Reasoning Evaluation in an Era of Saturation","created":"2025-11-03","cited_by_count":7,"area":"lr"},{"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,"area":"lr"},{"id":"2606.15079","title":"Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale","created":"2026-06-13","cited_by_count":6,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2510.23458","title":"BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents","created":"2025-10-27","cited_by_count":5,"area":"lr"},{"id":"2604.03144","title":"InCoder-32B-Thinking: Industrial Code World Model for Thinking","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2604.05164","title":"Not All Turns Are Equally Hard: Adaptive Thinking Budgets For Efficient Multi-Turn Reasoning in Agents","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2511.21638","title":"Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF","created":"2025-11-26","cited_by_count":3,"area":"lr"},{"id":"2605.07182","title":"Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control","created":"2026-05-08","cited_by_count":3,"area":"lr"},{"id":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2510.26495","title":"Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration","created":"2025-10-30","cited_by_count":2,"area":"lr"},{"id":"2601.08225","title":"User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale","created":"2026-01-13","cited_by_count":2,"area":"lr"},{"id":"2602.01709","title":"ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation","created":"2026-02-02","cited_by_count":2,"area":"lr"},{"id":"2605.07339","title":"Tools as Continuous Flow for Evolving Agentic Reasoning","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2607.25816","title":"Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL","created":"2026-07-28","cited_by_count":2,"area":"lr"},{"id":"2608.01678","title":"Progressive Agent Skill Generation via Reinforcement Learning","created":"2026-08-03","cited_by_count":2,"area":"lr"},{"id":"2602.19519","title":"Ada-RS: Adaptive Rejection Sampling for Selective Thinking","created":"2026-02-23","cited_by_count":1,"area":"lr"},{"id":"2605.22177","title":"Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles","created":"2026-05-21","cited_by_count":1,"area":"lr"},{"id":"2605.27820","title":"EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2608.00181","title":"Cross-Benchmark Generalization in Long-Horizon Agents","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2608.17587","title":"Write, Execute, Refine: From Skill Follower to Skill Optimizer via Reinforcement Learning from Execution Feedback","created":"2026-08-18","cited_by_count":1,"area":"lr"},{"id":"2608.26432","title":"SpeechGym: An Audio-Native Gym for Training Voice Agents via Reinforcement Learning","created":"2026-08-26","cited_by_count":1,"area":"lr"},{"id":"2609.29050","title":"SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL","created":"2026-09-24","cited_by_count":1,"area":"lr"},{"id":"2609.36641","title":"Inducing Process Supervision from Outcome-Only Reinforcement Learning","created":"2026-09-29","cited_by_count":1,"area":"lr"},{"id":"2510.22898","title":"On Generalization in Agentic Tool Calling: CoreThink Agentic Reasoner and MAVEN Dataset","created":"2025-10-27","cited_by_count":0,"area":"lr"},{"id":"2601.03286","title":"HyperCLOVA X 32B Think","created":"2026-01-03","cited_by_count":0,"area":"lr"},{"id":"2602.02160","title":"D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2604.26173","title":"Entropy Centroids as Intrinsic Rewards for Test-Time Scaling","created":"2026-04-28","cited_by_count":0,"area":"lr"},{"id":"2605.07699","title":"DRIP-R: A Benchmark for Decision-Making and Reasoning Under Real-World Policy Ambiguity in the Retail Domain","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2605.07926","title":"AgentEscapeBench: Evaluating Out-of-Domain Tool-Grounded Reasoning in LLM Agents","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2608.07885","title":"Reason Wide, Not Deep: Amortizing the Reasoning Premium into Distilled Skills","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.08146","title":"Long SKILL Compliance as Logical Reasoning: Closure-Grounded Detection with Scaling-Guided On-Policy Distillation","created":"2026-08-08","cited_by_count":0,"area":"lr"},{"id":"2608.13667","title":"Second Thought: Reasoning in Parallel as LLM Agents Act and Observe","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2608.26235","title":"The Reasoning Tax: Token Economics of LLM Reasoning Across Task Types and Deployment Contexts","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2608.30650","title":"Geometry of Divergence: Tracking Hidden-State Trajectories for Adaptive Multi-Turn Reasoning","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"id":"2609.13060","title":"CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.13134","title":"Rethinking Heterogeneous System Disaggregation for Subquadratic Attention","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.13866","title":"The Filter Metric is Safety-Critical: Phantom Advantages in Group-Relative RL under Shaped Rewards","created":"2026-09-12","cited_by_count":0,"area":"lr"},{"id":"2609.15066","title":"Salesforce Koa: An Enterprise Language Model for Agentic Tool Use","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.16887","title":"QART: A Quantum-Classical Hybrid Architecture for Long-Horizon Reasoning -- Exploring a Conditional Path toward Quantum Scaling","created":"2026-09-15","cited_by_count":0,"area":"lr"},{"id":"2609.20089","title":"UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2610.13438","title":"Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.18683","title":"ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}