Related papers: Practical MCTS-based Query Optimization: A Reprodu…
Monte Carlo tree search (MCTS) is a popular choice for solving sequential anytime problems. However, it depends on a numeric feedback signal, which can be difficult to define. Real-time MCTS is a variant which may only rarely encounter…
This work presents the first study of using the popular Monte Carlo Tree Search (MCTS) method combined with dedicated heuristics for solving the Weighted Vertex Coloring Problem. Starting with the basic MCTS algorithm, we gradually…
Large language models demonstrate exceptional performance in simple code generation tasks but still face challenges in tackling complex problems. These challenges may stem from insufficient reasoning and problem decomposition capabilities.…
Sequential decision-making under uncertainty is present in many important problems. Two popular approaches for tackling such problems are reinforcement learning and online search (e.g., Monte Carlo tree search). While the former learns a…
Physics-based simulations and learning-based models are vital for complex robotics tasks like deformable object manipulation and liquid handling. However, these models often struggle with accuracy due to epistemic uncertainty or the…
Diverse, top-k, and top-quality planning are concerned with the generation of sets of solutions to sequential decision problems. Previously this area has been the domain of classical planners that require a symbolic model of the problem…
Recent advances in large language models have demonstrated considerable potential in scientific domains such as drug repositioning. However, their effectiveness remains constrained when reasoning extends beyond the knowledge acquired during…
This paper introduces the Constrained Monte Carlo Tree Search (CMCTS) framework to enhance the mathematical reasoning capabilities of Large Language Models (LLM). By incorporating a constrained action space, Process Reward Model (PRM), and…
Much current research in AI and games is being devoted to Monte Carlo search (MCS) algorithms. While the quest for a single unified MCS algorithm that would perform well on all problems is of major interest for AI, practitioners often know…
In large domains, Monte-Carlo tree search (MCTS) is required to estimate the values of the states as efficiently and accurately as possible. However, the standard update rule in backpropagation assumes a stationary distribution for the…
Online planning in continuous state, action, and observation spaces remains challenging for autonomous systems. While Monte Carlo Tree Search (MCTS) scales effectively via sampling, most continuous (PO)MDP solvers do not exploit…
Today's automated vehicles lack the ability to cooperate implicitly with others. This work presents a Monte Carlo Tree Search (MCTS) based approach for decentralized cooperative planning using macro-actions for automated vehicles in…
LLM-powered systems require complex multi-step decision-making abilities to solve real-world tasks, yet current planning approaches face a trade-off between the high latency of inference-time search and the limited generalization of…
Inspired by recent successes of Monte-Carlo tree search (MCTS) in a number of artificial intelligence (AI) application domains, we propose a model-based reinforcement learning (RL) technique that iteratively applies MCTS on batches of…
Autonomous mobile robots enable increased flexibility of manufacturing systems. The design and operating strategy of such a fleet of robots requires careful consideration of both fixed and operational costs. In this paper, a Monte-Carlo…
PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection Siyuan Cheng, Bozhong Tian, Yanchao Hao, Zheng Wei Published: 06 Apr 2026, Last Modified: 06 Apr 2026 ACL 2026 Findings Conference, Area Chairs, Reviewers,…
Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g., incorrect plans or…
We present Model Predictive Trees (MPT), a receding horizon tree search algorithm that improves its performance by reusing information efficiently. Whereas existing solvers reuse only the highest-quality trajectory from the previous…
In this paper we propose a novel reinforcement learning based model for sequence tagging, referred to as MM-Tag. Inspired by the success and methodology of the AlphaGo Zero, MM-Tag formalizes the problem of sequence tagging with a Monte…
Although RLVR has become an essential component for developing advanced reasoning skills in language models, contemporary studies have documented training plateaus after thousands of optimization steps, i.e., notable decreases in…