{"ID":2823271,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.00938","arxiv_id":"2601.00938","title":"Rate-Distortion Analysis of Compressed Query Delegation with Low-Rank Riemannian Updates","abstract":"Bounded-context agents fail when intermediate reasoning exceeds an effective working-memory budget. We study compressed query delegation (CQD): (i) compress a high-dimensional latent reasoning state into a low-rank tensor query, (ii) delegate the minimal query to an external oracle, and (iii) update the latent state via Riemannian optimization on fixed-rank manifolds. We give a math-first formulation: CQD is a constrained stochastic program with a query-budget functional and an oracle modeled as a noisy operator. We connect CQD to classical rate-distortion and information bottleneck principles, showing that spectral hard-thresholding is optimal for a natural constrained quadratic distortion problem, and we derive convergence guarantees for Riemannian stochastic approximation under bounded oracle noise and smoothness assumptions. Empirically, we report (A) a 2,500-item bounded-context reasoning suite (BBH-derived tasks plus curated paradox instances) comparing CQD against chain-of-thought baselines under fixed compute and context; and (B) a human \"cognitive mirror\" benchmark (N=200) measuring epistemic gain and semantic drift across modern oracles.","short_abstract":"Bounded-context agents fail when intermediate reasoning exceeds an effective working-memory budget. We study compressed query delegation (CQD): (i) compress a high-dimensional latent reasoning state into a low-rank tensor query, (ii) delegate the minimal query to an external oracle, and (iii) update the latent state vi...","url_abs":"https://arxiv.org/abs/2601.00938","url_pdf":"https://arxiv.org/pdf/2601.00938v1","authors":"[\"Faruk Alpay\",\"Bugra Kilictas\"]","published":"2026-01-02T14:04:58Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"math.OC\"]","methods":"[]","has_code":false}