Planning

DynaThink: Fast or Slow? A Dynamic Decision-Making Framework for Large Language Models EMNLP 2024 EDC: Effective and Efficient Dialog Comprehension For Dialog State Tracking NAACL 2024 Efficient Constraint Generation for Stochastic Shortest Path Problems AAAI 2024 Efficient Dynamics Modeling in Interactive Environments with Koopman Theory ICLR 2024 Efficient Monte Carlo Tree Search via On-the-Fly State-Conditioned Action Abstraction UAI 2024 Efficient Planning with Latent Diffusion ICLR 2024 Efficient skill acquisition for insertion tasks in obstructed environments L4DC 2024 Efficient Variational Sequential Information Control AISTATS 2024 Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making NeurIPS 2024 Empowering Multi-step Reasoning across Languages via Program-Aided Language Models EMNLP 2024 End-to-End Beam Retrieval for Multi-Hop Question Answering NAACL 2024 End-to-End Learning of LTLf Formulae by Faithful LTLf Encoding AAAI 2024 Enhancing Agent Learning through World Dynamics Modeling EMNLP 2024 Enhancing Large Language Models through Transforming Reasoning Problems into Classification Tasks COLING 2024 Enhancing LLM Reasoning via Vision-Augmented Prompting NeurIPS 2024 Entropy-Reinforced Planning with Large Language Models for Drug Discovery ICML 2024 EPO: Hierarchical LLM Agents with Environment Preference Optimization EMNLP 2024 ERA-CoT: Improving Chain-of-Thought through Entity Relationship Analysis ACL 2024 Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning ICLR 2024 Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation ACL 2024 Experience as Source for Anticipation and Planning: Experiential Policy Learning for Target-driven Recommendation Dialogues EMNLP 2024 Experience-based multi-agent path finding with narrow corridors RSS 2024 Expert-level protocol translation for self-driving labs NeurIPS 2024 EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning EMNLP 2024 Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following NeurIPS 2024