{"total":41,"rows":[{"id":"2411.13543","title":"BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games","created":"2024-11-20","cited_by_count":146,"area":"lr"},{"id":"2407.11511","title":"Multi-Step Reasoning with Large Language Models, a Survey","created":"2024-07-16","cited_by_count":143,"area":"lr"},{"id":"2410.14157","title":"Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning","created":"2024-10-18","cited_by_count":135,"area":"lr"},{"id":"2410.21333","title":"Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse","created":"2024-10-27","cited_by_count":109,"area":"lr"},{"id":"2501.08603","title":"Monte Carlo Tree Search for Comprehensive Exploration in LLM-Based Automatic Heuristic Design","created":"2025-01-15","cited_by_count":109,"area":"lr"},{"id":"2408.00764","title":"AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation","created":"2024-08-01","cited_by_count":83,"area":"lr"},{"id":"2403.04121","title":"Can Large Language Models Reason and Plan?","created":"2024-03-07","cited_by_count":82,"area":"lr"},{"id":"2407.01863","title":"VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs","created":"2024-07-02","cited_by_count":47,"area":"lr"},{"id":"2406.05673","title":"Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples","created":"2024-06-09","cited_by_count":30,"area":"lr"},{"id":"2402.06529","title":"Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity","created":"2024-02-09","cited_by_count":27,"area":"lr"},{"id":"2410.03524","title":"Steering Large Language Models between Code Execution and Textual Reasoning","created":"2024-10-04","cited_by_count":24,"area":"lr"},{"id":"2405.13966","title":"On the Brittle Foundations of ReAct Prompting for Agentic Large Language Models","created":"2024-05-22","cited_by_count":17,"area":"lr"},{"id":"2504.03930","title":"Have Large Language Models Learned to Reason? A Characterization via 3-SAT Phase Transition","created":"2025-04-04","cited_by_count":14,"area":"lr"},{"id":"2507.11662","title":"Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification","created":"2025-07-15","cited_by_count":14,"area":"lr"},{"id":"2507.00711","title":"Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories","created":"2025-07-01","cited_by_count":10,"area":"lr"},{"id":"2502.06813","title":"Policy Guided Tree Search for Enhanced LLM Reasoning","created":"2025-02-04","cited_by_count":9,"area":"lr"},{"id":"2512.23167","title":"SPIRAL: Symbolic LLM Planning via Grounded and Reflective Search","created":"2025-12-29","cited_by_count":7,"area":"lr"},{"id":"2406.10479","title":"Unlocking Large Language Model's Planning Capabilities with Maximum Diversity Fine-tuning","created":"2024-06-15","cited_by_count":6,"area":"lr"},{"id":"2408.16081","title":"Towards Logically Sound Natural Language Reasoning with Logic-Enhanced Language Model Agents","created":"2024-08-28","cited_by_count":5,"area":"lr"},{"id":"2410.03348","title":"Dolphin: A Programmable Framework for Scalable Neurosymbolic Learning","created":"2024-10-04","cited_by_count":5,"area":"lr"},{"id":"2510.12979","title":"DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping","created":"2025-10-14","cited_by_count":5,"area":"lr"},{"id":"2506.06008","title":"Token Signature: Predicting Chain-of-Thought Gains with Token Decoding Feature in Large Language Models","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2503.10241","title":"SCOOP: A Framework for Proactive Collaboration and Social Continual Learning through Natural Language Interaction andCausal Reasoning","created":"2025-03-13","cited_by_count":3,"area":"lr"},{"id":"2510.16374","title":"Before you <think>, monitor: Implementing Flavell's metacognitive framework in LLMs","created":"2025-10-18","cited_by_count":3,"area":"lr"},{"id":"2604.00555","title":"Ontology-Constrained Neural Reasoning in Enterprise Agentic Systems: A Neurosymbolic Architecture for Domain-Grounded AI Agents","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2607.26977","title":"TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning","created":"2026-07-29","cited_by_count":2,"area":"lr"},{"id":"2608.20686","title":"CDRL: Certification-Driven Reinforcement Learning for Neutrino Flavor Model Discovery","created":"2026-08-21","cited_by_count":2,"area":"lr"},{"id":"2407.09985","title":"A Training Data Recipe to Accelerate A* Search with Language Models","created":"2024-07-13","cited_by_count":1,"area":"lr"},{"id":"2603.01571","title":"Beyond Length Scaling: Synergizing Breadth and Depth for Generative Reward Models","created":"2026-03-02","cited_by_count":1,"area":"lr"},{"id":"2604.09338","title":"Mind the Gap Between Spatial Reasoning and Acting! Step-by-Step Evaluation of Agents With Spatial-Gym","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2412.04645","title":"REL: Working out is all you need","created":"2024-12-05","cited_by_count":0,"area":"lr"},{"id":"2507.18775","title":"Initial Steps in Integrating Large Reasoning and Action Models for Service Composition","created":"2025-07-24","cited_by_count":0,"area":"lr"},{"id":"2510.07516","title":"CompassLLM: A Multi-Agent Approach toward Geo-Spatial Reasoning for Popular Path Query","created":"2025-10-08","cited_by_count":0,"area":"lr"},{"id":"2510.22235","title":"CGoT: A Novel Inference Mechanism for Embodied Multi-Agent Systems Using Composable Graphs of Thoughts","created":"2025-10-25","cited_by_count":0,"area":"lr"},{"id":"2602.15867","title":"Playing With AI: How Do State-Of-The-Art Large Language Models Perform in the 1977 Text-Based Adventure Game Zork?","created":"2026-01-27","cited_by_count":0,"area":"lr"},{"id":"2605.15333","title":"Zero-Shot Goal Recognition with Large Language Models","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2607.04854","title":"CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs","created":"2026-07-06","cited_by_count":0,"area":"lr"},{"id":"2607.15313","title":"Position: Quantum Program Generation Must Prioritize Validity Over Probabilistic Scaling","created":"2026-07-15","cited_by_count":0,"area":"lr"},{"id":"2607.18443","title":"Computational models of pragmatic reasoning with flexible generation of meaning and expression alternatives","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2608.12626","title":"LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2609.39069","title":"CORE: Conflict-Oriented Reasoning Elimination for Verifiable Language-Model Search","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}