AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

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

Joshua Ong Jun Leang, Yu Zhao, Mihaela C. Stoian, Wenda Li, Shay B Cohen, Eleonora Giunchiglia

ICML 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Machine learning for physical simulation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add MCTS slot ordering to ReFusion (ablation)ReFusion 7B · HumanEvalPass@1 (%): 62.05% -> 78.37%Improved
add MCTS slot ordering to ReFusion (ablation)ReFusion 7B · MBPPPass@1 (%): 54.12% -> 73.57%Improved
add MCTS slot ordering to ReFusion (ablation)ReFusion 7B · ARCPass@1 (%): 87.98% -> 88.68%Improved
add MCTS slot ordering to ReFusion (ablation)ReFusion 7B · MATH500Pass@1 (%): 42.90% -> 47.80%Improved
replace sequential slot order with MCTS ordering (ablation)McDiffuSE · Average of 6 benchmarksPass@1 (%): 58.29% -> 68.52%Improved
replace random slot order with MCTS ordering (ablation)McDiffuSE · Average of 6 benchmarksPass@1 (%): 43.10% -> 68.52%Improved
increase simulations N_sim from 30 to 270 at low exploration c=2 (ablation)McDiffuSE · MBPP and MATH500accuracy: mean entropy 1.41 -> 1.18 bits; accuracy decreasesHurt
increase simulations N_sim from 30 to 270 at high exploration c=100 (ablation)McDiffuSE · policy entropymean entropy (bits): 1.4176 -> 1.4340No clear effect
increase exploration constant c (ablation)McDiffuSE · benchmarksaccuracyImproved
raise N_sim from 30 to 270 (ablation)McDiffuSE · accuracy and costaccuracy / compute: improvement < 2% while computational cost increases nine-foldMixed
set tau=0.5 and lambda=0.3 versus lambda=0.0 (no confidence mixing) (ablation)McDiffuSE · MATH500accuracy (%): 45.60 -> 48.20Improved
add MCTS to ReFusion versus Best-of-N and Beam Search at matched compute (ablation)McDiffuSE · Average of 6 benchmarks (LM-Eval-Harness)accuracy (%): Best-of-N 61.82, Beam Search 63.84 -> DiffuSearch 74.53Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy