{"total":29,"rows":[{"id":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199,"area":"lr"},{"id":"2512.08296","title":"Towards a Science of Scaling Agent Systems","created":"2025-12-09","cited_by_count":138,"area":"lr"},{"id":"2506.24119","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","created":"2025-06-30","cited_by_count":100,"area":"lr"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2505.13886","title":"Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning","created":"2025-05-20","cited_by_count":32,"area":"lr"},{"id":"2505.13426","title":"G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning","created":"2025-05-19","cited_by_count":29,"area":"lr"},{"id":"2505.15692","title":"TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning","created":"2025-05-21","cited_by_count":28,"area":"lr"},{"id":"2503.23064","title":"VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language Models","created":"2025-03-29","cited_by_count":26,"area":"lr"},{"id":"2503.12349","title":"SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?","created":"2025-03-16","cited_by_count":24,"area":"lr"},{"id":"2505.16135","title":"Sudoku-Bench: Evaluating creative reasoning with Sudoku variants","created":"2025-05-22","cited_by_count":22,"area":"lr"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2509.03581","title":"Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents","created":"2025-09-03","cited_by_count":20,"area":"lr"},{"id":"2506.01341","title":"TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Models","created":"2025-06-02","cited_by_count":13,"area":"lr"},{"id":"2507.07644","title":"FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations","created":"2025-07-10","cited_by_count":13,"area":"lr"},{"id":"2505.04364","title":"Benchmarking LLMs' Swarm intelligence","created":"2025-05-07","cited_by_count":10,"area":"lr"},{"id":"2602.20901","title":"SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models","created":"2026-02-24","cited_by_count":6,"area":"lr"},{"id":"2604.11741","title":"Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games","created":"2026-04-13","cited_by_count":6,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2505.10543","title":"Reasoning Capabilities of Large Language Models on Dynamic Tasks","created":"2025-05-15","cited_by_count":4,"area":"lr"},{"id":"2508.16821","title":"PuzzleJAX: A Benchmark for Reasoning and Learning","created":"2025-08-22","cited_by_count":4,"area":"lr"},{"id":"2505.16928","title":"Beyond Needle(s) in the Embodied Haystack: Environment, Architecture, and Training Considerations for Long Context Reasoning","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2506.22992","title":"MARBLE: A Hard Benchmark for Multimodal Spatial Reasoning and Planning","created":"2025-06-28","cited_by_count":3,"area":"lr"},{"id":"2508.19988","title":"AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2607.22732","title":"Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning","created":"2026-07-22","cited_by_count":1,"area":"lr"},{"id":"2510.05972","title":"LexiCon: a Benchmark for Planning under Temporal Constraints in Natural Language","created":"2025-10-07","cited_by_count":0,"area":"lr"},{"id":"2602.15858","title":"State Design Matters: How Representations Shape Dynamic Reasoning in Large Language Models","created":"2026-01-25","cited_by_count":0,"area":"lr"},{"id":"2605.07021","title":"Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2609.34214","title":"GlyphBench: A Playground for Language-Model Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.34769","title":"LongPuzzleBench: Evaluating GUI Agents on Long-Horizon Visual Puzzles","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}