Chemical reasoning usually involves complex, multi-step processes that demand precise calculations, where even minor errors can lead to cascading failures. Furthermore, large language models (LLMs) encounter difficulties handling domain-specific formulas, executing reasoning steps accurately, and integrating code effectively when tackling chemical reasoning tasks. To address these challenges, we present ChemAgent, a novel framework designed to improve the performance of LLMs through a dynamic, self-updating library. This library is developed by decomposing chemical tasks into sub-tasks and compiling these sub-tasks into a structured collection that can be referenced for future queries. Then, when presented with a new problem, ChemAgent retrieves and refines pertinent information from the library, which we call memory, facilitating effective task decomposition and the generation of solutions. Our method designs three types of memory and a library-enhanced reasoning component, enabling LLMs to improve over time through experience. Experimental results on four chemical reasoning datasets from SciBench demonstrate that ChemAgent achieves performance gains of up to 46% (GPT-4), significantly outperforming existing methods. Our findings suggest substantial potential for future applications, including tasks such as drug discovery and materials science. Our code can be found at https://github.com/gersteinlab/chemagent

Prospective students face the challenging task of selecting a university program that will shape their academic and professional careers. For decision-makers and support services, it is often time-consuming and extremely difficult to match personal interests with suitable programs due to the vast and complex catalogue information available. This paper presents the first information system that provides students with efficient recommendations based on both program content and personal preferences. BERTopic, a powerful topic modeling algorithm, is used that leverages text embedding techniques to generate topic representations. It enables us to mine interest topics from all course descriptions, representing the full body of knowledge taught at the institution. Underpinned by the student's individual choice of topics, a shortlist of the most relevant programs is computed through statistical backtracking in the knowledge map, a novel characterization of the program-course relationship. This approach can be applied to a wide range of educational settings, including professional and vocational training. A case study at a post-secondary school with 80 programs and over 5,000 courses shows that the system provides immediate and effective decision support. The presented interest topics are meaningful, leading to positive effects such as serendipity, personalization, and fairness, as revealed by a qualitative study involving 65 students. Over 98% of users indicated that the recommendations aligned with their interests, and about 94% stated they would use the tool in the future. Quantitative analysis shows the system can be configured to ensure fairness, achieving 98% program coverage while maintaining a personalization score of 0.77. These findings suggest that this real-time, user-centered, data-driven system could improve the program selection process.

Spoken language datasets are vital for advancing linguistic research, Natural Language Processing, and speech technology. However, resources dedicated to Italian, a linguistically rich and diverse Romance language, remain underexplored compared to major languages like English or Mandarin. This survey provides a comprehensive analysis of 66 spoken Italian datasets, highlighting their characteristics, methodologies, and applications. The datasets are categorized by speech type, source and context, and demographic and linguistic features, with a focus on their utility in fields such as Automatic Speech Recognition, emotion detection, and education. Challenges related to dataset scarcity, representativeness, and accessibility are discussed alongside recommendations for enhancing dataset creation and utilization. The full dataset inventory is publicly accessible via GitHub and archived on Zenodo, serving as a valuable resource for researchers and developers. By addressing current gaps and proposing future directions, this work aims to support the advancement of Italian speech technologies and linguistic research.

We develop automatic speech recognition (ASR) systems for stories told by Afrikaans and isiXhosa preschool children. Oral narratives provide a way to assess children's language development before they learn to read. We consider a range of prior child-speech ASR strategies to determine which is best suited to this unique setting. Using Whisper and only 5 minutes of transcribed in-domain child speech, we find that additional in-domain adult data (adult speech matching the story domain) provides the biggest improvement, especially when coupled with voice conversion. Semi-supervised learning also helps for both languages, while parameter-efficient fine-tuning helps on Afrikaans but not on isiXhosa (which is under-represented in the Whisper model). Few child-speech studies look at non-English data, and even fewer at the preschool ages of 4 and 5. Our work therefore represents a unique validation of a wide range of previous child-speech ASR strategies in an under-explored setting.

This study explores the use of artificial intelligence (AI) as a complementary tool for grading essay-type questions in higher education, focusing on its consistency with human grading and potential to reduce biases. Using 70 handwritten exams from an introductory sociology course, we evaluated generative pre-trained transformers (GPT) models' performance in transcribing and scoring students' responses. GPT models were tested under various settings for both transcription and grading tasks. Results show high similarity between human and GPT transcriptions, with GPT-4o-mini outperforming GPT-4o in accuracy. For grading, GPT demonstrated strong correlations with the human grader scores, especially when template answers were provided. However, discrepancies remained, highlighting GPT's role as a "second grader" to flag inconsistencies for assessment reviewing rather than fully replace human evaluation. This study contributes to the growing literature on AI in education, demonstrating its potential to enhance fairness and efficiency in grading essay-type questions.

While Large Language Models (LLMs) have demonstrated remarkable capabilities in scientific tasks, existing evaluation frameworks primarily assess their performance using rich contextual inputs, overlooking their ability to generate novel ideas from minimal information. We introduce LiveIdeaBench, a comprehensive benchmark that evaluates LLMs' scientific creativity and divergent thinking capabilities using single-keyword prompts. Drawing from Guilford's creativity theory, our framework employs a dynamic panel of state-of-the-art LLMs to assess generated ideas across four key dimensions: originality, feasibility, fluency, and flexibility. Through extensive experimentation with 20 leading models across 1,180 keywords spanning 18 scientific domains, we reveal that scientific creative ability shows distinct patterns from general intelligence metrics. Notably, our results demonstrate that models like QwQ-32B-preview achieve comparable creative performance to top-tier models like o1-preview, despite significant gaps in their general intelligence scores. These findings highlight the importance of specialized evaluation frameworks for scientific creativity and suggest that the development of creative capabilities in LLMs may follow different trajectories than traditional problem-solving abilities.

Nowadays transformer-based Large Language Models (LLM) for code generation tasks usually apply sampling and filtering pipelines. Due to the sparse reward problem in code generation tasks caused by one-token incorrectness, transformer-based models will sample redundant programs till they find a correct one, leading to low efficiency. To overcome the challenge, we incorporate Experience Replay (ER) in the fine-tuning phase, where codes and programs produced are stored and will be replayed to give the LLM agent a chance to learn from past experiences. Based on the spirit of ER, we introduce a novel approach called BTP pipeline which consists of three phases: beam search sampling, testing phase, and prioritized experience replay phase. The approach makes use of failed programs collected by code models and replays programs with high Possibility and Pass-rate Prioritized value (P2Value) from the replay buffer to improve efficiency. P2Value comprehensively considers the possibility of transformers' output and pass rate and can make use of the redundant resources caused by the problem that most programs collected by LLMs fail to pass any tests. We empirically apply our approach in several LLMs, demonstrating that it enhances their performance in code generation tasks and surpasses existing baselines.

We present a gradient-based meta-learning framework for rapid adaptation of neural state-space models (NSSMs) for black-box system identification. When applicable, we also incorporate domain-specific physical constraints to improve the accuracy of the NSSM. The major benefit of our approach is that instead of relying solely on data from a single target system, our framework utilizes data from a diverse set of source systems, enabling learning from limited target data, as well as with few online training iterations. Through benchmark examples, we demonstrate the potential of our approach, study the effect of fine-tuning subnetworks rather than full fine-tuning, and report real-world case studies to illustrate the practical application and generalizability of the approach to practical problems with physical-constraints. Specifically, we show that the meta-learned models result in improved downstream performance in model-based state estimation in indoor localization and energy systems.

Recent advancements in large language models (LLMs) and multimodal speech-text models have laid the groundwork for seamless voice interactions, enabling real-time, natural, and human-like conversations. Previous models for voice interactions are categorized as native and aligned. Native models integrate speech and text processing in one framework but struggle with issues like differing sequence lengths and insufficient pre-training. Aligned models maintain text LLM capabilities but are often limited by small datasets and a narrow focus on speech tasks. In this work, we introduce MinMo, a Multimodal Large Language Model with approximately 8B parameters for seamless voice interaction. We address the main limitations of prior aligned multimodal models. We train MinMo through multiple stages of speech-to-text alignment, text-to-speech alignment, speech-to-speech alignment, and duplex interaction alignment, on 1.4 million hours of diverse speech data and a broad range of speech tasks. After the multi-stage training, MinMo achieves state-of-the-art performance across various benchmarks for voice comprehension and generation while maintaining the capabilities of text LLMs, and also facilitates full-duplex conversation, that is, simultaneous two-way communication between the user and the system. Moreover, we propose a novel and simple voice decoder that outperforms prior models in voice generation. The enhanced instruction-following capabilities of MinMo supports controlling speech generation based on user instructions, with various nuances including emotions, dialects, and speaking rates, and mimicking specific voices. For MinMo, the speech-to-text latency is approximately 100ms, full-duplex latency is approximately 600ms in theory and 800ms in practice. The MinMo project web page is https://funaudiollm.github.io/minmo, and the code and models will be released soon.

Service robots are increasingly entering the home to provide domestic tasks for residents. However, when working in an open, dynamic, and unstructured home environment, service robots still face challenges such as low intelligence for task execution and poor long-term autonomy (LTA), which has limited their deployment. As the basis of robotic task execution, environment modeling has attracted significant attention. This integrates core technologies such as environment perception, understanding, and representation to accurately recognize environmental information. This paper presents a comprehensive survey of environmental modeling from a new task-executionoriented perspective. In particular, guided by the requirements of robots in performing domestic service tasks in the home environment, we systematically review the progress that has been made in task-execution-oriented environmental modeling in four respects: 1) localization, 2) navigation, 3) manipulation, and 4) LTA. Current challenges are discussed, and potential research opportunities are also highlighted.