cs.LGNov 18, 2026

Online State-Representation Adaptation under Synthetic Interaction-Cue Remapping

Authors: Bin Yin

Organizations: School of Psychology, Fujian Normal University

Abstract

When cues change what they predict, continuing to update a learned mapping may help an agent choose the appropriate action. We tested this in a one-step synthetic task by comparing a logistic state predictor that continued to learn from state labels with the same predictor frozen at transfer. We evaluated ten conditions in six held-out environments, with 1,296 paired runs per condition and 1,296,000 transfer records in total. Late action accuracy was 93.39% with online updates and 64.63% with frozen coefficients, a paired difference of 28.76 [8.73, 53.19] percentage points (95% environment-bootstrap interval). A direct policy reached 95.65% using the same predictions with a different action threshold. A contextual bandit reached 94.23% and earned more cumulative utility than the adaptive predictor. The bandit used the reward of its chosen action, which in this task reveals the true state when combined with that action. Weights based on development history lowered cumulative utility relative to neutral weights (difference -3.45 [-4.48, -2.43]). The adaptive predictor outperformed its frozen counterpart in late accuracy in each of the six test environments. The other comparisons show how the choice of action threshold and the information available in feedback affect what can be attributed to online adaptation.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Data Attribution in Adaptive Learning

    Apr 6, 2026Amit Kiran RegeTraining Data AttributionAdaptive Learning

  2. Sandwich-Residuals: Parameter-Efficient Test-time Adaptation of World Models

    Sep 18, 2026Krishnam Soni, Aditya Sehgal, Vedant Dave +1Test-Time AdaptationLatent World Models

  3. Where Should LLM Agents Adapt at Test Time? In Context, in Weights, or Both

    Nov 15, 2026Parsa Mirtaheri, Mohammadreza Armandpour, Keivan Alizadeh +5Test-Time AdaptationExperience Learning for LLM Agents