Latest AI News and Developments

A curated selection of the most significant AI news and developments from trusted sources. Each article is directly linked to its original publication for full context and details.

Using Reasoning Models to Generate Search Heuristics that Solve Open Instances of Combinatorial Design Problems

Published by arXiv AI on June 2, 2025

arXiv:2505.23881v1 Announce Type: new Abstract: Large Language Models (LLMs) with reasoning are trained to iteratively generate and refine their answers before finalizing them, which can help with applications to mathematics and code generation. We apply code generation with reasoning LLMs to a specific task in the mathematical field of combinatorial design. This field studies diverse types of...

OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Published by arXiv AI on June 2, 2025

arXiv:2505.23885v1 Announce Type: new Abstract: Large Language Model (LLM)-based multi-agent systems show promise for automating real-world tasks but struggle to transfer across domains due to their domain-specific nature. Current approaches face two critical shortcomings: they require complete architectural redesign and full retraining of all components when applied to new domains. We introduce...

Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve

Published by arXiv AI on June 2, 2025

arXiv:2505.23946v1 Announce Type: new Abstract: Recent studies show that LLMs possess different skills and specialize in different tasks. In fact, we observe that their varied performance occur in several levels of granularity. For example, in the code optimization task, code LLMs excel at different optimization categories and no one dominates others. This observation prompts the question of how...

InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback

Published by arXiv AI on June 2, 2025

arXiv:2505.23950v1 Announce Type: new Abstract: As multimodal large models (MLLMs) continue to advance across challenging tasks, a key question emerges: What essential capabilities are still missing? A critical aspect of human learning is continuous interaction with the environment -- not limited to language, but also involving multimodal understanding and generation. To move closer to...

MSQA: Benchmarking LLMs on Graduate-Level Materials Science Reasoning and Knowledge

Published by arXiv AI on June 2, 2025

arXiv:2505.23982v1 Announce Type: new Abstract: Despite recent advances in large language models (LLMs) for materials science, there is a lack of benchmarks for evaluating their domain-specific knowledge and complex reasoning abilities. To bridge this gap, we introduce MSQA, a comprehensive evaluation benchmark of 1,757 graduate-level materials science questions in two formats: detailed...

Sources

This curated overview brings together articles from the following trusted sources:

• arXiv AI

Note: All content is directly sourced from the original publications. Each article is properly cited with links to the original sources. For the most up-to-date information, please visit the original articles through the provided links.