SFT supplies entangled compositional traces of atomic skills and routing modules; RL identifies those modules and enables recombination on novel compositions outside the SFT support.
Task generalization with autoregressive compositional structure: Can learning fromd tasks generalize tod {t} tasks?arXiv preprint arXiv:2502.08991
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
LLMs show strong spatial generalization to unseen maps in shortest-path tasks but fail length scaling due to recursive instability, with data coverage setting hard limits.
citing papers explorer
-
From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning
SFT supplies entangled compositional traces of atomic skills and routing modules; RL identifies those modules and enables recombination on novel compositions outside the SFT support.
-
Generalization in LLM Problem Solving: The Case of the Shortest Path
LLMs show strong spatial generalization to unseen maps in shortest-path tasks but fail length scaling due to recursive instability, with data coverage setting hard limits.