Large Language Models (LLMs) are key technologies driving intelligent systems to handle multiple tasks. To meet the demands of various tasks, an increasing number of LLMs-driven experts with diverse capabilities have been developed, accompanied by corresponding benchmarks to evaluate their performance. This paper proposes the Bench-CoE framework, which enables Collaboration of Experts (CoE) by effectively leveraging benchmark evaluations to achieve optimal performance across various tasks. Bench-CoE includes a set of expert models, a router for assigning tasks to corresponding experts, and a benchmark dataset for training the router. Moreover, we formulate Query-Level and Subject-Level approaches based on our framework, and analyze the merits and drawbacks of these two approaches. Finally, we conduct a series of experiments with vary data distributions on both language and multimodal tasks to validate that our proposed Bench-CoE outperforms any single model in terms of overall performance. We hope this method serves as a baseline for further research in this area. The code is available at \url{https://github.com/ZhangXJ199/Bench-CoE}.

Large Language Models (LLMs) have extended their capabilities beyond language generation to interact with external systems through tool calling, offering powerful potential for real-world applications. However, the phenomenon of tool hallucinations, which occur when models improperly select or misuse tools, presents critical challenges that can lead to flawed task execution and increased operational costs. This paper investigates the concept of reliable tool calling and highlights the necessity of addressing tool hallucinations. We systematically categorize tool hallucinations into two main types: tool selection hallucination and tool usage hallucination. To mitigate these issues, we propose a reliability-focused alignment framework that enhances the model's ability to accurately assess tool relevance and usage. By proposing a suite of evaluation metrics and evaluating on StableToolBench, we further demonstrate the effectiveness of our framework in mitigating tool hallucination and improving the overall system reliability of LLM tool calling.

We propose utilizing background operators for mathematical reasoning in large language models (LLMs). To achieve this, we define a set of fundamental mathematical predicates as the basic building blocks. For each mathematical problem, we develop a Prolog solution that includes problem-specific predicates and intermediate predicates derived from these background operators, ensuring that each solution adheres to the defined operator set. We introduce the MATH-Prolog corpus, which is derived from the counting and probability categories of the MATH corpus. For efficient data augmentation, we apply K-fold cross-validated self-training. This method incrementally generates new Prolog solutions for each fold, incorporating those verified as correct into the training set throughout the model training process. Our experimental results demonstrate that 5-fold crossvalidated self-training effectively identifies new, accurate Prolog solutions, achieving an accuracy of 84.6% on the cross-validated set, and 84.8% on the test set during fine-tuning the Meta-Llama-3.1-8B-Instruct model. This approach successfully uncovers new solutions with fully computable inference steps for previously unseen problems. Additionally, incorporating the background mathematical predicates into the prompt enhances solution coverage.

Sequential recommendation (SR) aims to model the sequential dependencies in users' historical interactions to better capture their evolving interests. However, existing SR approaches primarily rely on collaborative data, which leads to limitations such as the cold-start problem and sub-optimal performance. Meanwhile, despite the success of large language models (LLMs), their application in industrial recommender systems is hindered by high inference latency, inability to capture all distribution statistics, and catastrophic forgetting. To this end, we propose a novel Pre-train, Align, and Disentangle (PAD) paradigm to empower recommendation models with LLMs. Specifically, we first pre-train both the SR and LLM models to get collaborative and textual embeddings. Next, a characteristic recommendation-anchored alignment loss is proposed using multi-kernel maximum mean discrepancy with Gaussian kernels. Finally, a triple-experts architecture, consisting aligned and modality-specific experts with disentangled embeddings, is fine-tuned in a frequency-aware manner. Experiments conducted on three public datasets demonstrate the effectiveness of PAD, showing significant improvements and compatibility with various SR backbone models, especially on cold items. The implementation code and datasets will be publicly available.

As the strength of Large Language Models (LLMs) has grown over recent years, so too has interest in their use as the underlying models for autonomous agents. Although LLMs demonstrate emergent abilities and broad expertise across natural language domains, their inherent unpredictability makes the implementation of LLM agents challenging, resulting in a gap between related research and the real-world implementation of such systems. To bridge this gap, this paper frames actionable insights and considerations from the research community in the context of established application paradigms to enable the construction and facilitate the informed deployment of robust LLM agents. Namely, we position relevant research findings into four broad categories--Planning, Memory, Tools, and Control Flow--based on common practices in application-focused literature and highlight practical considerations to make when designing agentic LLMs for real-world applications, such as handling stochasticity and managing resources efficiently. While we do not conduct empirical evaluations, we do provide the necessary background for discussing critical aspects of agentic LLM designs, both in academia and industry.

Language models have rapidly evolved, predominantly focusing on English while often neglecting extensive pretraining in other languages. This approach has required initiatives to adapt powerful, English-centric models to other linguistic contexts through finetuning. For Dutch, such a recent endeavour is ``GEITje'' a model originally derived from the English-based Mistral 7B. Building on this fundamental work, the current research extends the capabilities of GEITje by supervised finetuning on newly created high-quality synthetic conversational datasets, along with an additional preference alignment procedure on a synthetic feedback dataset. Both the developed models and the created datasets are openly available.

The application of deep learning methods, particularly foundation models, in biological research has surged in recent years. These models can be text-based or trained on underlying biological data, especially omics data of various types. However, comparing the performance of these models consistently has proven to be a challenge due to differences in training data and downstream tasks. To tackle this problem, we developed an architecture-agnostic benchmarking approach that, instead of evaluating the models directly, leverages entity representation vectors from each model and trains simple predictive models for each benchmarking task. This ensures that all types of models are evaluated using the same input and output types. Here we focus on gene properties collected from professionally curated bioinformatics databases. These gene properties are categorized into five major groups: genomic properties, regulatory functions, localization, biological processes, and protein properties. Overall, we define hundreds of tasks based on these databases, which include binary, multi-label, and multi-class classification tasks. We apply these benchmark tasks to evaluate expression-based models, large language models, protein language models, DNA-based models, and traditional baselines. Our findings suggest that text-based models and protein language models generally outperform expression-based models in genomic properties and regulatory functions tasks, whereas expression-based models demonstrate superior performance in localization tasks. These results should aid in the development of more informed artificial intelligence strategies for biological understanding and therapeutic discovery. To ensure the reproducibility and transparency of our findings, we have made the source code and benchmark data publicly accessible for further investigation and expansion at github.com/BiomedSciAI/gene-benchmark.

Protein design has become a critical method in advancing significant potential for various applications such as drug development and enzyme engineering. However, protein design methods utilizing large language models with solely pretraining and fine-tuning struggle to capture relationships in multi-modal protein data. To address this, we propose ProtDAT, a de novo fine-grained framework capable of designing proteins from any descriptive protein text input. ProtDAT builds upon the inherent characteristics of protein data to unify sequences and text as a cohesive whole rather than separate entities. It leverages an innovative multi-modal cross-attention, integrating protein sequences and textual information for a foundational level and seamless integration. Experimental results demonstrate that ProtDAT achieves the state-of-the-art performance in protein sequence generation, excelling in rationality, functionality, structural similarity, and validity. On 20,000 text-sequence pairs from Swiss-Prot, it improves pLDDT by 6%, TM-score by 0.26, and reduces RMSD by 1.2 {\AA}, highlighting its potential to advance protein design.

Abstract--Large language models (LLMs) have shown impressive capabilities in generating program code, opening exciting opportunities for applying program synthesis to games. In this work, we explore the potential of LLMs to directly synthesize usable code for a wide range of gaming applications, focusing on two programming languages, Python and Java. We use an evolutionary hill-climbing algorithm, where the mutations and seeds of the initial programs are controlled by LLMs. For Python, the framework covers various game-related tasks, including five miniature versions of Atari games, ten levels of Baba is You, an environment inspired by Asteroids, and a maze generation task. For Java, the framework contains 12 games from the TAG tabletop games framework. Across 29 tasks, we evaluated 12 language models for Python and 8 for Java. Our findings suggest that the performance of LLMs depends more on the task than on model size. While larger models generate more executable programs, these do not always result in higher-quality solutions but are much more expensive. No model has a clear advantage, although on any specific task, one model may be better. Trying many models on a problem and using the best results across them is more reliable than using just one.

This document contains detailed information about the prompts used in the experimental process discussed in the paper "Toward Automating Agent-based Model Generation: A Benchmark for Model Extraction using Question-Answering Techniques". The paper aims to utilize Question-answering (QA) models to extract the necessary information to implement Agent-based Modeling (ABM) from conceptual models. It presents the extracted information in formats that can be read by both humans and computers (i.e., JavaScript Object Notation (JSON)), enabling manual use by humans and auto-code generation by Large Language Models (LLM).