Reasoning trace placement swings long-context accuracy by 50 points, Trace-as-State technique shows

dair_ai · x · 2026-09-04

A practical technique for reasoning models: place the reasoning trace before the long-context block on a fresh pass instead of appending it after. Because Transformers process causally, earlier-derived state can guide rereading. On GraphWalks Parents, DeepSeek V4 Pro Preview jumps from 29.2% (baseline) and 43.0% (trace appended) to 81.8% with Trace as State; GLM-5.2 improves from 66.4% / 83.2% similarly. The author notes that providing conditions first can require exponentially less memory in the worst case for causal processors. A near-free context-ordering change with huge accuracy payoff.

Related event: Placing Reasoning Traces Before Context Boosts Long-Context Accuracy by Up to 50 Points(2 posts)→

Original post →

More from Models

Models channel →