Archives AI News

$p$-less Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding

arXiv:2509.23234v1 Announce Type: new Abstract: Obtaining high-quality outputs from Large Language Models (LLMs) often depends upon the choice of a sampling-based decoding strategy to probabilistically choose the next token at each generation step. While a variety of such sampling methods…

AutoEP: LLMs-Driven Automation of Hyperparameter Evolution for Metaheuristic Algorithms

arXiv:2509.23189v1 Announce Type: new Abstract: Dynamically configuring algorithm hyperparameters is a fundamental challenge in computational intelligence. While learning-based methods offer automation, they suffer from prohibitive sample complexity and poor generalization. We introduce AutoEP, a novel framework that bypasses training entirely…

On The Sample Complexity Bounds In Bilevel Reinforcement Learning

arXiv:2503.17644v4 Announce Type: replace-cross Abstract: Bilevel reinforcement learning (BRL) has emerged as a powerful framework for aligning generative models, yet its theoretical foundations, especially sample complexity bounds, remain underexplored. In this work, we present the first sample complexity bound for…

A Partition Cover Approach to Tokenization

arXiv:2501.06246v3 Announce Type: replace-cross Abstract: Tokenization is the process of encoding strings into tokens of a fixed vocabulary size, and is widely utilized in Natural Language Processing applications. The leading tokenization algorithm today is Byte-Pair Encoding (BPE), which formulates the…

Ocassionally Secure: A Comparative Analysis of Code Generation Assistants

arXiv:2402.00689v2 Announce Type: replace-cross Abstract: $ $Large Language Models (LLMs) are being increasingly utilized in various applications, with code generations being a notable example. While previous research has shown that LLMs have the capability to generate both secure and insecure…

AI-Enhanced Distributed Channel Access for Collision Avoidance in Future Wi-Fi 8

arXiv:2509.23154v1 Announce Type: new Abstract: The exponential growth of wireless devices and stringent reliability requirements of emerging applications demand fundamental improvements in distributed channel access mechanisms for unlicensed bands. Current Wi-Fi systems, which rely on binary exponential backoff (BEB), suffer…

Prover Agent: An Agent-Based Framework for Formal Mathematical Proofs

arXiv:2506.19923v3 Announce Type: replace Abstract: We present Prover Agent, a novel AI agent for automated theorem proving that integrates large language models (LLMs) with a formal proof assistant, Lean. Prover Agent coordinates an informal reasoning LLM, a formal prover model,…