cs.AINov 17, 2026

Proximal Targets: Training Looped Refiners on Problems with Many Correct Answers

Authors: Syed Affan Daimi

Organizations: International Institute of Information Technology, Hyderabad, India.

Abstract

Looped refiners such as HRM and TRM apply one small network repeatedly to a draft answer, and deep supervision trains every pass toward one stored answer per puzzle. We prove that when a puzzle has many correct answers this target sets a loss floor that no model capacity removes, and that the loss-minimising pass blends the answers into an invalid grid. We propose the proximal target: train each pass toward the correct answer nearest to its own input, found by scanning a list of answers, by a search solver started at the draft, or within a band of quality set by a knob; correct answers become fixed points, and a pass only has to make fewer errors than its input has for the loop to converge, which its training loss bounds. With the same 1.7M-parameter network and 5 seeds, the proximal target solves 98.8% of Sudoku puzzles with 2-64 answers (standard target: 2.5%), 93.8% of sparse puzzles with more than 10,000 answers without any list of answers (0.0%), and 90.9% of 200-node 3-colourings after training on graphs of at most 50 nodes (36.9%), and different random starts end at different answers. Against GRAM, a stochastic-latent reasoner, a single run is correct far more often (98.8% vs. 57.7%) and twenty runs find more of the answers (53.6% vs. 37.4%), while GRAM is slightly ahead on its own 10-node colouring benchmark; in Scrabble the knob becomes a calibrated strength dial.

Figures & tables

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Resample the Answer: Where to Spend Test-Time Compute in Recursive Reasoning

    Oct 12, 2026Maxime IllouzRecursive Reasoning ModelsInference-Time Search

  2. Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning

    Sep 1, 2026Mariia Drozdova, Aidan Sirbu, Pietro Miotti +4Constraint SatisfactionAlgorithmic Reasoning