analiza aiqbench
AutoIndex introduces an automated search over executable document transformation programs to optimize retrieval quality, effectively treating preprocessing as a learnable objective rather than static configuration. By using agents to diagnose failures and synthesize updates, the system achieves significant gains in recall and nDCG across heterogeneous tasks while keeping standard retrievers like BM25 fixed. This approach shifts the paradigm of information retrieval by making representation learning an explicit optimization target within AI systems.
AutoIndex: Learning Representation Programs for Retrieval
arXiv:2607.18603v1 Announce Type: cross Abstract: We present AutoIndex, a framework for learning representation programs: executable transformations that map raw documents into the representations exposed to a retrieval system. Rather than tuning retrievers, rerankers, or a small set of preprocessing hyperparameters, AutoIndex searches over programs that slice, enrich, normalize, reweight, or reorganize documents before indexing. At each iteration, AutoIndex performs validation-guided program search, in which agents diagnose failures of the current program and synthesize candidate updates, retaining only updates that improve retrieval quality under the resulting index. We evaluate AutoIndex on CRUMB, a benchmark of heterogeneous retrieval tasks, with BM25 held fixed across all experiments. The learned programs improve recall over a static full-document BM25 baseline on all 8 tasks, with average gains of +8.4% in Recall@100 and +8.3% in nDCG@10, and largest gains of +30.5% in Recall@100 and +43.6% in nDCG@10. These results suggest that document representation should not be treated as a fixed preprocessing choice made before retrieval begins, but as an explicit optimization target. Code to reproduce our results is available at https://github.com/auto-index/autoindex.
Abstract:We present AutoIndex, a framework for learning representation programs: executable transformations that map raw documents into the representations exposed to a retrieval system. Rather than tuning retrievers, rerankers, or a small set of preprocessing hyperparameters, AutoIndex searches over programs that slice, enrich, normalize, reweight, or reorganize documents before indexing. At each iteration, AutoIndex performs validation-guided program search, in which agents diagnose failures of the current program and synthesize candidate updates, retaining only updates that improve retrieval quality under the resulting index. We evaluate AutoIndex on CRUMB, a benchmark of heterogeneous retrieval tasks, with BM25 held fixed across all experiments. The learned programs improve recall over a static full-document BM25 baseline on all 8 tasks, with average gains of +8.4% in Recall@100 and +8.3% in nDCG@10, and largest gains of +30.5% in Recall@100 and +43.6% in nDCG@10. These results suggest that document representation should not be treated as a fixed preprocessing choice made before retrieval begins, but as an explicit optimization target. Code to reproduce our results is available at this https URL.
Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
arXiv:2607.18603 [cs.IR]
(or arXiv:2607.18603v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2607.18603 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.
Text integral sub licența deschisă a publicației · 273 cuvinte
Subiecte conexe
Self-Supervised Representations for Binary Program Clustering: From Empirical Study to Retrieval-Augmented Learning
arXiv · 4 aug. 2026
HyperFL: Query-Adaptive Representation Learning for Software Fault Localization
arXiv · 5 aug. 2026
Amazon is investing in the Lean Focused Research Organization
Amazon Science · 26 iul. 2026
Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval
arXiv · 6 oct. 2026