AINeutralarXiv – CS AI · May 287/10
🧠Researchers reverse-engineered a Sokoban-playing RNN trained with model-free reinforcement learning and discovered that the network encodes planning strategies through specialized neural channels that represent directional movements and learned transition models. The findings demonstrate that neural networks can develop interpretable planning algorithms without explicit supervision, with path channels and extension kernels working together to implement bidirectional search and backtracking.
AIBullisharXiv – CS AI · Apr 67/10
🧠Research shows that large language models significantly outperform traditional AI planning algorithms on complex block-moving problems, tracking theoretical optimality limits with near-perfect precision. The study suggests LLMs may use algorithmic simulation and geometric memory to bypass exponential combinatorial complexity in planning tasks.
AINeutralarXiv – CS AI · Mar 46/103
🧠Researchers introduce ViPlan, the first benchmark for comparing Vision-Language Model planning approaches, finding that VLM-as-grounder methods excel in visual tasks like Blocksworld while VLM-as-planner methods perform better in household robotics scenarios. The study reveals fundamental limitations in current VLMs' visual reasoning abilities, with Chain-of-Thought prompting showing no consistent benefits.
AINeutralarXiv – CS AI · 20h ago6/10
🧠Researchers have developed a machine-learning framework that learns to create admissible heuristics for optimal planning by leveraging cost partitioning and Lagrangian duality. The approach uses graph neural networks with Weisfeiler-Leman algorithms to generate cost weights that guarantee admissibility by construction, marking the first learned heuristic with formal optimality guarantees.
AINeutralarXiv – CS AI · 20h ago6/10
🧠Researchers provide a rigorous mathematical framework showing how Active Inference and Expected Free Energy (EFE) minimization can be decomposed into Variational Free Energy (VFE) minimization with explicit entropy corrections. The work clarifies the theoretical foundations of EFE-based planning by identifying which corrections are necessary for different decision-making scenarios, demonstrated through grid-world experiments.
AINeutralarXiv – CS AI · 2d ago6/10
🧠Researchers introduce an optimized inference method for generative AI planning models that combines classical Open-Closed List search with learned generative and heuristic components. The approach demonstrates superior computational efficiency and solution quality compared to existing neurosymbolic and classical solvers across combinatorial planning domains.
AINeutralarXiv – CS AI · 3d ago6/10
🧠Researchers propose a learned 'rerooter' approach to improve Levin Tree Search for complex single-agent problems, eliminating the need for explicit subgoal generation. Three rerooter designs exploit state-space structure, learned heuristics, or hybrid signals to achieve scalable search with lower computational overhead and improved online training efficiency.
AINeutralarXiv – CS AI · May 116/10
🧠Researchers present the first finite-time theoretical analysis of Monte Carlo Tree Search (MCTS) applied to Partially Observable Markov Decision Processes (POMDPs), bridging a critical gap in algorithmic guarantees. The paper introduces Voro-POMCPOW, which uses Voronoi cell partitioning for continuous observation spaces, proving high-probability bounds on value estimates while maintaining competitive empirical performance.
AIBullisharXiv – CS AI · Mar 36/104
🧠Researchers developed a message passing approach for Expected Free Energy minimization that transforms complex combinatorial search problems into tractable inference problems. The method enables more efficient AI agent planning and exploration under uncertainty, outperforming conventional approaches in test environments.
AIBullisharXiv – CS AI · Mar 115/10
🧠Researchers present GenePlan, a framework that uses large language models with evolutionary algorithms to generate domain-specific planners for classical planning tasks in PDDL. The system achieved a 0.91 SAT score across eight benchmark domains, nearly matching state-of-the-art performance while significantly outperforming other LLM-based approaches.
🧠 GPT-4
AINeutralarXiv – CS AI · Mar 44/102
🧠Researchers studied diffusion-based model predictive control in discrete domains using Tetris, finding that feasibility constraints are necessary and shorter planning horizons outperform longer ones. The study reveals structural challenges with discrete diffusion planners, particularly misalignment issues with DQN critics that produce high decision regret.
