{"total":82,"rows":[{"id":"2410.05229","title":"GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models","created":"2024-10-07","cited_by_count":550,"area":"lr"},{"id":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498,"area":"lr"},{"id":"2405.14831","title":"HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models","created":"2024-05-23","cited_by_count":281,"area":"rag"},{"id":"2409.12183","title":"To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning","created":"2024-09-18","cited_by_count":263,"area":"lr"},{"id":"2409.13373","title":"LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench","created":"2024-09-20","cited_by_count":94,"area":null},{"id":"2502.11221","title":"PlanGenLLMs: A Modern Survey of LLM Planning Capabilities","created":"2025-02-16","cited_by_count":83,"area":null},{"id":"2505.12514","title":"Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought","created":"2025-05-18","cited_by_count":77,"area":"lr"},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71,"area":"lr"},{"id":"2508.01191","title":"Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens","created":"2025-08-02","cited_by_count":43,"area":"lr"},{"id":"2405.20625","title":"Robust Planning with LLM-Modulo Framework: Case Study in Travel Planning","created":"2024-05-31","cited_by_count":34,"area":null},{"id":"2405.00972","title":"CACTUS: Chemistry Agent Connecting Tool-Usage to Science","created":"2024-05-02","cited_by_count":33,"area":"agents"},{"id":"2407.10031","title":"LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments","created":"2024-07-14","cited_by_count":32,"area":"agents"},{"id":"2602.15785","title":"This human study did not involve human subjects: Validating LLM simulations as behavioral evidence","created":"2026-02-17","cited_by_count":29,"area":null},{"id":"2503.02324","title":"PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models","created":"2025-03-04","cited_by_count":22,"area":"lr"},{"id":"2505.11581","title":"Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis","created":"2025-05-16","cited_by_count":22,"area":null},{"id":"2410.01769","title":"Quantifying Generalization Complexity for Large Language Models","created":"2024-10-02","cited_by_count":18,"area":null},{"id":"2406.10196","title":"TRIP-PAL: Travel Planning with Guarantees by Combining Large Language Models and Automated Planners","created":"2024-06-14","cited_by_count":17,"area":null},{"id":"2507.21931","title":"Post-Training Large Language Models via Reinforcement Learning from Self-Feedback","created":"2025-07-29","cited_by_count":15,"area":"lr"},{"id":"2408.06904","title":"Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives","created":"2024-08-13","cited_by_count":13,"area":"lr"},{"id":"2412.10380","title":"Challenges in Human-Agent Communication","created":"2024-11-28","cited_by_count":12,"area":"agents"},{"id":"2502.04728","title":"Generating Symbolic World Models via Test-time Scaling of Large Language Models","created":"2025-02-07","cited_by_count":12,"area":"wm"},{"id":"2407.07561","title":"FLAIR: Feeding via Long-horizon AcquIsition of Realistic dishes","created":"2024-07-10","cited_by_count":10,"area":null},{"id":"2409.01806","title":"LASP: Surveying the State-of-the-Art in Large Language Model-Assisted AI Planning","created":"2024-09-03","cited_by_count":9,"area":null},{"id":"2410.19923","title":"Language Agents Meet Causality -- Bridging LLMs and Causal World Models","created":"2024-10-25","cited_by_count":9,"area":"wm"},{"id":"2411.08253","title":"Open-World Task and Motion Planning via Vision-Language Model Generated Constraints","created":"2024-11-13","cited_by_count":9,"area":"mllm"},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2406.05506","title":"Towards a Benchmark for Causal Business Process Reasoning with LLMs","created":"2024-06-08","cited_by_count":7,"area":"lr"},{"id":"2506.14968","title":"FEAST: A Flexible Mealtime-Assistance System Towards In-the-Wild Personalization","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2509.01398","title":"The Need for Verification in AI-Driven Scientific Discovery","created":"2025-09-01","cited_by_count":7,"area":null},{"id":"2511.07568","title":"Procedural Knowledge Improves Agentic LLM Workflows","created":"2025-11-10","cited_by_count":7,"area":"agents"},{"id":"2404.06750","title":"Frontier AI Ethics: Anticipating and Evaluating the Societal Impacts of Language Model Agents","created":"2024-04-10","cited_by_count":5,"area":"agents"},{"id":"2411.11260","title":"Large corpora and large language models: a replicable method for automating grammatical annotation","created":"2024-11-18","cited_by_count":5,"area":null},{"id":"2502.13776","title":"A Knapsack by Any Other Name: Presentation impacts LLM performance on NP-hard problems","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2503.02238","title":"Haste Makes Waste: Evaluating Planning Abilities of LLMs for Efficient and Feasible Multitasking with Time Constraints Between Actions","created":"2025-03-04","cited_by_count":5,"area":"lr"},{"id":"2505.03985","title":"LogiDebrief: A Signal-Temporal Logic based Automated Debriefing Approach with Large Language Models Integration","created":"2025-05-06","cited_by_count":5,"area":null},{"id":"2409.00861","title":"Harnessing the Power of Semi-Structured Knowledge and LLMs with Triplet-Based Prefiltering for Question Answering","created":"2024-09-01","cited_by_count":4,"area":null},{"id":"2504.11711","title":"The Hitchhiker's Guide to Program Analysis, Part II: Deep Thoughts by LLMs","created":"2025-04-16","cited_by_count":4,"area":null},{"id":"2510.08044","title":"Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation","created":"2025-10-09","cited_by_count":4,"area":"lr"},{"id":"2510.18699","title":"Fetch.ai: An Architecture for Modern Multi-Agent Systems","created":"2025-10-21","cited_by_count":4,"area":"agents"},{"id":"2601.19752","title":"Agentic Design Patterns: A System-Theoretic Framework","created":"2026-01-27","cited_by_count":4,"area":"agents"},{"id":"2410.03062","title":"Image First or Text First? Optimising the Sequencing of Modalities in Large Language Model Prompting and Reasoning Tasks","created":"2024-10-04","cited_by_count":3,"area":"lr"},{"id":"2503.02972","title":"LINGOLY-TOO: Disentangling Reasoning from Knowledge with Templatised Orthographic Obfuscation","created":"2025-03-04","cited_by_count":3,"area":"lr"},{"id":"2505.09246","title":"Autofocus Retrieval: An Effective Pipeline for Multi-Hop Question Answering With Semi-Structured Knowledge","created":"2025-05-14","cited_by_count":3,"area":null},{"id":"2512.02841","title":"Cross-Lingual Prompt Steerability: Towards Accurate and Robust LLM Behavior across Languages","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2407.03652","title":"Over the Edge of Chaos? Excess Complexity as a Roadblock to Artificial General Intelligence","created":"2024-07-04","cited_by_count":2,"area":null},{"id":"2408.16667","title":"Iterative Graph Alignment","created":"2024-08-29","cited_by_count":2,"area":null},{"id":"2411.17912","title":"Can LLMs plan paths in the real world?","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2505.20964","title":"Semantic Communication meets System 2 ML: How Abstraction, Compositionality and Emergent Languages Shape Intelligence","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2506.05412","title":"Vision-Language Models Mistake Head Orientation for Gaze Direction: Nonverbal Conversation Cues","created":"2025-06-04","cited_by_count":2,"area":"mllm"},{"id":"2507.11408","title":"KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning?","created":"2025-07-15","cited_by_count":2,"area":"lr"},{"id":"2404.06946","title":"A Survey on the Integration of Generative AI for Critical Thinking in Mobile Networks","created":"2024-04-10","cited_by_count":1,"area":null},{"id":"2409.18989","title":"SC-Phi2: A Fine-tuned Small Language Model for StarCraft II Macromanagement Tasks","created":"2024-09-17","cited_by_count":1,"area":null},{"id":"2412.01752","title":"A Neurosymbolic Fast and Slow Architecture for Graph Coloring","created":"2024-12-02","cited_by_count":1,"area":null},{"id":"2502.18435","title":"What Makes the Preferred Thinking Direction for LLMs in Multiple-choice Questions?","created":"2025-02-25","cited_by_count":1,"area":"lr"},{"id":"2503.04848","title":"Three tiers of computation in transformers and in brain architectures","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2504.07463","title":"Enhanced Question-Answering for Skill-based learning using Knowledge-based AI and Generative AI","created":"2025-04-10","cited_by_count":1,"area":null},{"id":"2504.11200","title":"Mutual Understanding between People and Systems via Neurosymbolic AI and Knowledge Graphs","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2505.05318","title":"Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects","created":"2025-05-08","cited_by_count":1,"area":"mllm"},{"id":"2506.21783","title":"Evaluating List Construction and Temporal Understanding capabilities of Large Language Models","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2509.12987","title":"Toward PDDL Planning Copilot","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2511.20613","title":"Can Vibe Coding Beat Graduate CS Students? An LLM vs. Human Coding Tournament on Market-driven Strategic Planning","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2602.10329","title":"Are More Tokens Rational? Inference-Time Scaling in Language Models as Adaptive Resource Rationality","created":"2026-02-10","cited_by_count":1,"area":"lr"},{"id":"2606.27757","title":"Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2606.31399","title":"World-Model Collapse as a Phase Transition","created":"2026-06-30","cited_by_count":1,"area":"wm"},{"id":"2608.20237","title":"Rule-Compliant Visual Spatial Planning for Multimodal Large Language Models","created":"2026-08-20","cited_by_count":1,"area":"lr"},{"id":"2407.08824","title":"Proving that Cryptic Crossword Clue Answers are Correct","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2410.03904","title":"Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detection","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2501.00885","title":"Representation in large language models","created":"2025-01-01","cited_by_count":0,"area":null},{"id":"2501.07641","title":"GPT as a Monte Carlo Language Tree: A Probabilistic Perspective","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2505.04354","title":"Optimization Problem Solving Can Transition to Evolutionary Agentic Workflows","created":"2025-05-07","cited_by_count":0,"area":"agents"},{"id":"2506.00713","title":"AKReF: An argumentative knowledge representation framework for structured argumentation","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2508.05513","title":"Streamlining Admission with LOR Insights: AI-Based Leadership Assessment in Online Master's Program","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2509.22130","title":"Multi-Agent Path Finding via Offline RL and LLM Collaboration","created":"2025-09-26","cited_by_count":0,"area":"agents"},{"id":"2510.02660","title":"When Researchers Say Mental Model/Theory of Mind of AI, What Are They Really Talking About?","created":"2025-10-03","cited_by_count":0,"area":null},{"id":"2511.13458","title":"Trust in Vision-Language Models: Insights from a Participatory User Workshop","created":"2025-11-17","cited_by_count":0,"area":"mllm"},{"id":"2602.21947","title":"Algorithmic Blindness in Large Language Models: A Calibration Study of Performance Prediction","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2603.23800","title":"Object Search in Partially-Known Environments via LLM-informed Model-based Planning and Prompt Selection","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.07321","title":"Syntax Is Easy, Semantics Is Hard: Evaluating LLMs for LTL Translation","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.14851","title":"IFPV: An Integrated Multi-Agent Framework for Generative Operational Planning and High-Fidelity Plan Verification","created":"2026-05-14","cited_by_count":0,"area":"agents"},{"id":"2606.15686","title":"Recurrent Reasoning on Symbolic Puzzles with Sequence Models","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2607.08292","title":"Reverse Engineering Compliance: A Dual-Graph Verification Framework for Auditing Legacy IT Security Concepts","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2609.31460","title":"Segment-Level Agentic Topic Modeling for Improved Data Exploration and Resource Efficiency","created":"2026-09-25","cited_by_count":0,"area":"agents"}],"next_cursor":null}