Think While You Speak: Adaptive Computational Effort in Neural Dialogue Systems
Adaptive Cognitive Processing (ACP) is a minimal two-pathway architecture in which inference-time computation is input-dependent. A linear fast pathway answers familiar inputs by default, and a monitor checks the input against a small episodic memory, computing a novelty score that gates a deliberate MLP pathway. The system is implemented in pure NumPy on CPU, with analytical gradients verified against finite differences (max relative error 1.7e-9). On a 5,000-example synthetic task across three difficulty levels, ACP learns a clear routing gradient: it deliberates on 2.8% of easy inputs, 99.7% of medium inputs, and 99.2% of hard inputs, reaching 93.5% accuracy (mean of 10 seeds) versus 93.7% for an always-deliberate baseline while deliberating on only 67.2% of inputs. A 3-seed ablation removing the episodic novelty feature drops task accuracy from 94.3% to 73.7%, showing that the memory readout does real work. This is a mechanism study on a synthetic task; dialogue is the motivating application, not the experimental setting.
Authors
- Syed Syab Ahmad Shah (ORCID: https://orcid.org/0009-0003-9183-582X)
- Team MenteE AI
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-18
- DOI
- https://doi.org/10.5281/zenodo.24353177
- Primary Topic
- Speech and dialogue systems
- Type
- preprint