paper-with-me

Papers

Token Complexity Theory for AI-Augmented Computing

2026-06-10 · Jie Wang arxiv

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. This paradigm introduces a resource dimension that neither classical time nor space complexity captures: the cost of sending queries to and receiving responses from such a cluster. We introduce token complexity, a formal resource measure defined as the minimum expected token cost to achieve a specified level of output quality on a task, and develop a taxonomy classifying AI systems by the strength of their probabilistic properties. We develop token complexity within the framework of AI-Oracle Turing machines, in which a probabilistic Turing machine interacts with a stochastic oracle via dedicated query and response tapes. We prove basic theorems establishing that token complexity behaves as expected: monotonicity (higher quality costs more tokens), convexity (quality improvements become progressively more expensive), price sensitivity (small price changes produce bounded cost changes), and price-relativity of task ordering (the token complexity ordering of tasks can reverse depending on the query-to-response cost ratio). We prove that the complexity frontier, defined as the set of all feasible resource bounds in tokens, time, and space, is non-empty, upward-closed, and convex.

📄 PDF Abstract BibTeX arXiv:2606.12647

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language QueriesCode Generation

Similar Papers 제목 키워드 기반

Optimal Scaling Laws for Efficiency Gains in a Theoretical Transformer-Augmented Sectional MoE Framework

2025-03-26 · Soham Sane

This paper introduces a theoretical framework for a Transformer-augmented, sectional Mixture-of-Experts (MoE) architecture that aims to enhance computational efficiency while preserving model scalability. Unlike conventi…

Computational EfficiencyMixture-of-Experts

A Theory for Token-Level Harmonization in Retrieval-Augmented Generation

2024-06-03 · Shicheng Xu, Liang Pang, HuaWei Shen, Xueqi Cheng

Retrieval-augmented generation (RAG) utilizes retrieved texts to enhance large language models (LLMs). Studies show that while RAG provides valuable external information (benefit), it may also mislead LLMs (detriment) wi…

RAGRetrievalRetrieval-augmented Generation

Single-pass Adaptive Image Tokenization for Minimum Program Search

2025-07-10 · Shivam Duggal, Sanghyun Byun, William T. Freeman, Antonio Torralba 외 arxiv

According to Algorithmic Information Theory (AIT) -- Intelligent representations compress data into the shortest possible program that can reconstruct its content, exhibiting low Kolmogorov Complexity (KC). In contrast, …

Representation LearningReinforcement Learning

Exceeding Computational Complexity Trial-and-Error Dynamic Action and Intelligence

2022-12-22 · Chuyu Xiong

Computational complexity is a core theory of computer science, which dictates the degree of difficulty of computation. There are many problems with high complexity that we have to deal, which is especially true for AI. T…

Reasoner-Executor-Synthesizer: Scalable Agentic Architecture with Static O(1) Context Window

2026-03-23 · Ivan Dobrovolskyi arxiv

Large Language Models (LLMs) deployed as autonomous agents commonly use Retrieval-Augmented Generation (RAG), feeding retrieved documents into the context window, which creates two problems: the risk of hallucination gro…