It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning Trajectories
Read the original on arXiv AI →The paper investigates whether large language models’ reasoning traces truly contain early, informative signals or merely reflect budget and difficulty confounds. Using a restart‑controlled truncation probe, the authors compare continuation success rates against from‑scratch restart curves across 178 problem‑model pairs, finding that only one case shows prefix‑limited success and that continuing a model’s own prefix generally outperforms restarting. A difficulty‑controlled test and two generation‑free analyses reveal that early internal signals do not carry outcome information beyond a problem‑difficulty baseline, underscoring the need for proper counterfactual controls.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.