Unit testing is an essential but resource-intensive step in software development, ensuring individual code units function correctly. This paper introduces AgoneTest, an automated evaluation framework for Large Language Model-generated (LLM) unit tests in Java. AgoneTest does not aim to propose a novel test generation algorithm; rather, it supports researchers and developers in comparing different LLMs and prompting strategies through a standardized end-to-end evaluation pipeline under realistic conditions. We introduce the Classes2Test dataset, which maps Java classes under test to their corresponding test classes, and a framework that integrates advanced evaluation metrics, such as mutation score and test smells, for a comprehensive assessment. Experimental results show that, for the subset of tests that compile, LLM-generated tests can match or exceed human-written tests in terms of coverage and defect detection. Our findings also demonstrate that enhanced prompting strategies contribute to test quality. AgoneTest clarifies the potential of LLMs in software testing and offers insights for future improvements in model design, prompt engineering, and testing practices.

Tokenization is used almost universally by modern language models, enabling efficient text representation using multi-byte or multi-character tokens. However, prior work has shown that tokenization can introduce distortion into the model's generations, an issue known as the Prompt Boundary Problem (PBP). For example, users are often advised not to end their prompts with a space because it prevents the model from including the space as part of the next token. While this heuristic is effective in English, the underlying PBP continues to affect languages such as Chinese as well as code generation, where tokens often do not line up with word and syntactic boundaries. In this work, we present an inference-time method to convert any autoregressive LM with a BPE tokenizer into a character-level or byte-level LM. Our method efficiently solves the PBP and is also able to unify the vocabularies of language models with different tokenizers, allowing one to ensemble LMs with different tokenizers at inference time or transfer the post-training from one model to another using proxy-tuning. We demonstrate in experiments that the ensemble and proxy-tuned models outperform their constituents on downstream evals. Code is available at https://github.com/SewoongLab/byte-sampler .

Many natural language processing systems operate over tokenizations of text to address the open-vocabulary problem. In this paper, we give and analyze an algorithm for the efficient construction of deterministic finite automata designed to operate directly on tokenizations produced by the popular byte pair encoding technique. This makes it possible to apply many existing techniques and algorithms to the tokenized case, such as pattern matching, equivalence checking of tokenization dictionaries, and composing tokenized languages in various ways.

The electricity consumption of buildings composes a major part of the city's energy consumption. Electricity consumption forecasting enables the development of home energy management systems resulting in the future design of more sustainable houses and a decrease in total energy consumption. Energy performance in buildings is influenced by many factors like ambient temperature, humidity, and a variety of electrical devices. Therefore, multivariate prediction methods are preferred rather than univariate. The Honda Smart Home US data set was selected to compare three methods for minimizing forecasting errors, MAE and RMSE: Artificial Neural Networks, Support Vector Regression, and Fuzzy Rule-Based Systems for Regression by constructing many models for each method on a multivariate data set in different time terms. The comparison shows that SVR is a superior method over the alternatives.

Israeli researchers have developed and tested an innovative artificial intelligence (AI) treatment to eliminate aggressive cancerous tumors, the Rambam Health Care Campus said Wednesday. The new method addresses sarcoma cancer tumors, known for their resistance to chemotherapy treatment, according to the largest hospital in northern Israel. Such tumors cannot be removed by surgery because of their proximity to vital organs, nerves, or blood vessels. To deal with these tumors, Rambam researchers choose radiation treatment with high intensity through a virtual grid, or net, to attack the tumors in a targeted manner. They created the method by using complex calculations of radiation intensity, along with AI to determine the path of radiation.

3-SAT problem is of great importance to many technical and scientific applications. This paper presents a new hybrid evolutionary algorithm for solving this satisfiability problem. 3-SAT problem has the huge search space and hence it is known as a NP-hard problem. So, deterministic approaches are not applicable in this context. Thereof, application of evolutionary processing approaches and especially PSO will be very effective for solving these kinds of problems. In this paper, we introduce a new evolutionary optimization technique based on PSO, Memetic algorithm and local search approaches. When some heuristics are mixed, their advantages are collected as well and we can reach to the better outcomes. Finally, we test our proposed algorithm over some benchmarks used by some another available algorithms. Obtained results show that our new method leads to the suitable results by the appropriate time. Thereby, it achieves a better result in compared with the existent approaches such as pure genetic algorithm and some verified types

The Baum-Welsh algorithm together with its derivatives and variations has been the main technique for learning Hidden Markov Models (HMM) from observational data. We present an HMM learning algorithm based on the non-negative matrix factorization (NMF) of higher order Markovian statistics that is structurally different from the Baum-Welsh and its associated approaches. The described algorithm supports estimation of the number of recurrent states of an HMM and iterates the non-negative matrix factorization (NMF) algorithm to improve the learned HMM parameters. Numerical examples are provided as well.