mlsanityData to 14 Oct 2026

Rate-Distortion Analysis of Compressed Query Delegation with Low-Rank Riemannian Updates

arXiv 2601.00938 ↗First posted 2 Jan 2026cs.CL math.OCcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 3 of its 16 references that are in the map. First posted on arXiv 2 Jan 2026.

Builds on

3 of 16 references.

References · 3

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  3. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,998

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Reasoning emerges from constrained inference manifolds in large language models
  2. 2026Compute Allocation for Reasoning-Intensive Retrieval Agents
  3. 2026Port-Hamiltonian Latent Deliberation: Mitigating the Deliberation Drift Cliff in Test-Time Compute Scaling
  4. 2026PACE: Prefix-Protected and Difficulty-Aware Compression for Efficient Reasoning
  5. 2026Preserving Mathematical Reasoning in Compressed Diffusion Language Models via Trajectory-Aware Low-Rank Approximation
  6. 2026Spend Bytes on Breadth: Precision-Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning
  7. 2026Efficient Reasoning via Constrained Optimization in Latent Space
  8. 2026SuperLocalMemory V3: Information-Geometric Foundations for Zero-LLM Enterprise Agent Memory