A probe-conditioned memory and Koopman MPC framework reduces seal-width tracking error from 0.25-0.40 mm to 0.049 mm in deadband-affected industrial dispensing by retrieving historical actuator-behavior records matched to a 16-move target probe.
Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches
3 Pith papers cite this work, alongside 5,521 external citations. Polarity classification is still indexing.
3
Pith papers citing it
5,521
external citations · OpenAlex
years
2026 3representative citing papers
DQA maintains persistent diagnostic state and aggregates retrievals at the root-cause level to reach 78.7% success on 150 enterprise IT scenarios versus 41.3% for standard multi-turn RAG while cutting average turns from 8.4 to 3.9.
HCoT integrates a heuristic classification model into LLM generation to structure reasoning, delivering higher accuracy and better token efficiency than CoT and ToT on inductive tasks and the 24 Game.
citing papers explorer
-
Probe-Conditioned Memory for Actuator-Deadband-Aware Koopman MPC in Industrial Sealing
A probe-conditioned memory and Koopman MPC framework reduces seal-width tracking error from 0.25-0.40 mm to 0.049 mm in deadband-affected industrial dispensing by retrieving historical actuator-behavior records matched to a 16-move target probe.
-
DQA: Diagnostic Question Answering for IT Support
DQA maintains persistent diagnostic state and aggregates retrievals at the root-cause level to reach 78.7% success on 150 enterprise IT scenarios versus 41.3% for standard multi-turn RAG while cutting average turns from 8.4 to 3.9.
-
Heuristic Classification of Thoughts Prompting (HCoT): Integrating Expert System Heuristics for Structured Reasoning into Large Language Models
HCoT integrates a heuristic classification model into LLM generation to structure reasoning, delivering higher accuracy and better token efficiency than CoT and ToT on inductive tasks and the 24 Game.