arXiv:2607. 06893v1 Announce Type: cross Abstract: The Stochastic-Oracle Turing Machine (SOTM) framework models AI-augmented computation as the interaction of a probabilistic Turing machine with an oracle whose responses are drawn from context-dependent distributions.
arXiv:2606. 24074v1 Announce Type: cross Abstract: Wang~\cite{Wang2026} introduced the Stochastic-Oracle Turing Machine (SOTM) framework and defined token complexity as the minimum expected cost of interacting with a stochastic oracle needed to attain a specified solution quality for a task.
arXiv:2606. 12647v1 Announce Type: cross Abstract: AI-augmented computing delegates natural language queries, code generation requests, and other open-ended tasks to a cluster of AI models that processes queries and generates responses.
arXiv:2609.35831v1 Announce Type: new Abstract: Modern large language models now support context windows of more than one million tokens, which has raised the question of whether retrieval-augmented...
arXiv:2607. 04281v1 Announce Type: cross Abstract: Semantic caching reduces the latency and cost of retrieval-augmented generation (RAG) by serving cached answers to semantically similar queries, but most existing methods do not model the time-varying freshness of open-web evidence.
arXiv:2606. 26836v1 Announce Type: new Abstract: Existing benchmarks typically report accuracy for a single model on a single run.
arXiv:2609.38006v1 Announce Type: new Abstract: Running a language model locally offers advantages in privacy, latency, and cost, but local hardware fits only small models, which are less capable tha...
arXiv:2604. 00660v2 Announce Type: replace-cross Abstract: Modern data warehouses extend SQL with semantic operators that invoke large language models on each qualifying row, making per-row inference orders of magnitude more expensive than traditional SQL.
The paper investigates how increasing inference-time computation—via wider beam search or sample‑plus‑vote—affects performance on grammar‑constrained text‑to‑SQL tasks for small language models. Using the Qwen2.5‑Instruct family (0.5B–7B parameters) on the Spider benchmark, the authors find that larger models consistently outperform higher inference compute on the same model size, and that beam search yields better accuracy than sample‑plus‑vote under matched budgets. These results suggest that, unlike unconstrained settings, scaling inference compute does not compensate for smaller model size when strict grammar constraints are applied.
arXiv:2609.07559v1 Announce Type: new Abstract: How do you validate a cheap, deterministic proxy for an oracle that is expensive, rate-limited, and non-stationary? We present a protocol built on adve...
Every memory-based knowledge editor in the SERAC lineage depends on a scope decision: given a query, does a stored edit apply? We report that current knowledge-editing benchmarks cannot measure this d...
arXiv:2607. 03436v1 Announce Type: new Abstract: Routing among large language models (LLMs) promises better quality at lower cost, motivated by the reported gap between learned routers and a per-instance oracle.
arXiv:2607. 17409v1 Announce Type: cross Abstract: We study the problem of sequentially evaluating a new large language model (LLM) on a fixed question set using historical performance data from prior LLMs.