A neuro-symbolic post-training pipeline lets a 4B transformer learn cubing heuristics that reach pass@5 of 53 on 100 SAT competition instances, matching the strongest symbolic baseline.
Psychological Bulletin , volume =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces MPT benchmark and PRefine method that models user preferences as evolving hypotheses to improve personalized tool calling accuracy with 1.24% of full-history token cost.
citing papers explorer
-
Learning How to Cube
A neuro-symbolic post-training pipeline lets a 4B transformer learn cubing heuristics that reach pass@5 of 53 on 100 SAT competition instances, matching the strongest symbolic baseline.
-
Latent Preference Modeling for Cross-Session Personalized Tool Calling
Introduces MPT benchmark and PRefine method that models user preferences as evolving hypotheses to improve personalized tool calling accuracy with 1.24% of full-history token cost.