Thought trees capture structural patterns in reasoning traces that predict LLM correctness on coding tasks, allowing a classifier to improve accuracy by retrying anomalous traces.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Playing Psychic: Using Thought Trees to Predict Reasoning Models Accuracy on Coding Tasks
Thought trees capture structural patterns in reasoning traces that predict LLM correctness on coding tasks, allowing a classifier to improve accuracy by retrying anomalous traces.