aiqbench analysis
The paper proposes RecRSI, an LLM-driven framework that organizes recommender-algorithm discovery around explicit "mechanism hypotheses," feeding each experiment's outcome back into later design choices. The reported gains are modest, about 8.5% NDCG@5 over the initial algorithms and 2.6% over the strongest competing method, and they come from four recommenders on four datasets, so robustness across broader settings remains to be shown. The code is public, which makes the claims checkable. For readers, the main interest is the workflow: using LLMs to run structured, evidence-guided search over model designs rather than one-off prompting.
RecRSI: Mechanism-Guided Discovery of Recommendation Algorithms
arXiv:2611.02487v1 Announce Type: cross Abstract: Improving recommendation algorithms for the Web requires coordinating interacting design choices and learning from experiments. We present RecRSI, an LLM-based research framework that uses mechanism hypotheses to organize algorithm discovery. Each hypothesis links a proposed mechanism change to a reference design, a rationale, and an expected observation. MechSpace derives implementable primitives and composition rules from the task source; Research Line uses this space and prior evidence to develop and test hypotheses; Mechanism Feedback carries outcomes and their design context into subsequent research. This organization makes each experiment inform which mechanisms to develop, revise, or combine next. Across four initial recommenders and four datasets, RecRSI yields average relative improvements of 8.48% in NDCG@5 and 6.88% in HR@5 over the initial algorithms, and 2.60% and 2.20%, respectively, over the strongest competing result for each setting and metric. Component and process studies link these gains to coordinated mechanism choices and evidence-guided follow-up. Our code is publicly available at https://github.com/DynamisG210/RecRSI.
Abstract:Improving recommendation algorithms for the Web requires coordinating interacting design choices and learning from experiments. We present RecRSI, an LLM-based research framework that uses mechanism hypotheses to organize algorithm discovery. Each hypothesis links a proposed mechanism change to a reference design, a rationale, and an expected observation. MechSpace derives implementable primitives and composition rules from the task source; Research Line uses this space and prior evidence to develop and test hypotheses; Mechanism Feedback carries outcomes and their design context into subsequent research. This organization makes each experiment inform which mechanisms to develop, revise, or combine next. Across four initial recommenders and four datasets, RecRSI yields average relative improvements of 8.48% in NDCG@5 and 6.88% in HR@5 over the initial algorithms, and 2.60% and 2.20%, respectively, over the strongest competing result for each setting and metric. Component and process studies link these gains to coordinated mechanism choices and evidence-guided follow-up. Our code is publicly available at this https URL.
Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
arXiv:2611.02487 [cs.IR]
(or arXiv:2611.02487v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2611.02487 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 255 words