Abstract
Techniques are described for bidirectional candidate generation in a recommendation pipeline using an active-feedback user simulation agent. An initial candidate set is retrieved using one or more retrieval paths. A user digital twin consumes a live session state, including an emotional-state embedding, and evaluates the candidates by predicting a session trajectory. When the predicted trajectory indicates low engagement, disengagement risk, or a coverage gap between predicted preference and available candidates, the agent generates a structured, machine-readable retrieval query (e.g., topic, content-type, social, negative, emotional, or mixing requests). A query handler executes the query to obtain additional candidates, forming an expanded candidate set. The agent may re-simulate and iteratively refine queries under iteration and latency policies. A planner orders items for presentation using the predicted trajectory over the expanded candidates.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Anonymous, "Active-Feedback User Simulation Agent for Bidirectional Content Retrieval in Recommendation Systems", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/10631