Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Leang, Joshua Ong Jun, Zhao, Yu, Stoian, Mihaela Cătălina, Li, Wenda, Cohen, Shay B., Giunchiglia, Eleonora
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914608198975488
author Leang, Joshua Ong Jun
Zhao, Yu
Stoian, Mihaela Cătălina
Li, Wenda
Cohen, Shay B.
Giunchiglia, Eleonora
author_facet Leang, Joshua Ong Jun
Zhao, Yu
Stoian, Mihaela Cătălina
Li, Wenda
Cohen, Shay B.
Giunchiglia, Eleonora
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12586
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models
Leang, Joshua Ong Jun
Zhao, Yu
Stoian, Mihaela Cătălina
Li, Wenda
Cohen, Shay B.
Giunchiglia, Eleonora
Artificial Intelligence
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.
title Can I Have Your Order? Monte-Carlo Tree Search for Slot Filling Ordering in Diffusion Language Models
topic Artificial Intelligence
url https://arxiv.org/abs/2602.12586