Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models
While plan-and-infill decoding in Masked Diffusion Models (MDMs) shows promise for mathematical and code reasoning, performance remains highly sensitive to slot infilling order, often yielding substantial output variance. We introduce McDiffuSE, a framework that formulates slot selection as decision making and optimises infilling orders through Monte Carlo Tree Search (MCTS). McDiffuSE uses look-ahead simulations to evaluate partial completions before commitment, systematically exploring the combinatorial space of generation orders. Experiments show an average improvement of 3.2% over autoregressive baselines and 8.0% over baseline plan-and-infill, with notable gains of 19.5% on MBPP and 4.9% on MATH500. Our analysis reveals that while McDiffuSE predominantly follows sequential ordering, incorporating non-sequential generation is essential for maximising performance. We observe that larger exploration constants, rather than increased simulations, are necessary to overcome model confidence biases and discover effective orderings. These findings establish MCTS-based planning as an effective approach for enhancing generation quality in MDMs.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingSlot FillingSimilar Papers 제목 키워드 기반
Monte Carlo Game Solver
We present a general algorithm to order moves so as to speedup exact game solvers. It uses online learning of playout policies and Monte Carlo Tree Search. The learned policy and the information in the Monte Carlo tree a…
Monte Carlo Search Algorithms Discovering Monte Carlo Tree Search Exploration Terms
Monte Carlo Tree Search and Monte Carlo Search have good results for many combinatorial problems. In this paper we propose to use Monte Carlo Search to design mathematical expressions that are used as exploration terms f…
Know your Enemy: Investigating Monte-Carlo Tree Search with Opponent Models in Pommerman
In combination with Reinforcement Learning, Monte-Carlo Tree Search has shown to outperform human grandmasters in games such as Chess, Shogi and Go with little to no prior domain knowledge. However, most classical use ca…
reinforcement-learningReinforcement LearningStarCraft II Build Order Optimization using Deep Reinforcement Learning and Monte-Carlo Tree Search
The real-time strategy game of StarCraft II has been posed as a challenge for reinforcement learning by Google's DeepMind. This study examines the use of an agent based on the Monte-Carlo Tree Search algorithm for optimi…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+2Monte Carlo Tree Search for Recipe Generation using GPT-2
Automatic food recipe generation methods provide a creative tool for chefs to explore and to create new, and interesting culinary delights. Given the recent success of large language models (LLMs), they have the potentia…
Recipe GenerationText Generation