Common gating signals for adaptive LLM compute have unstable directions across settings, and DIAL learns per-setting utility directions from signal-agnostic counterfactuals to outperform fixed-direction baselines.
Cats: Cali- brated test-time scaling for efficient llm reasoning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents
Common gating signals for adaptive LLM compute have unstable directions across settings, and DIAL learns per-setting utility directions from signal-agnostic counterfactuals to outperform fixed-direction baselines.