Recently, with the development of tool-calling capabilities in large language models (LLMs), these models have demonstrated significant potential for automating electronic design automation (EDA) flows by interacting with EDA tool APIs via EDA scripts. However, considering the limited understanding of EDA tools, LLMs face challenges in practical scenarios where diverse interfaces of EDA tools exist across different platforms. Additionally, EDA flow automation often involves intricate, long-chain tool-calling processes, increasing the likelihood of errors in intermediate steps. Any errors will lead to the instability and failure of EDA flow automation. To address these challenges, we introduce EDAid, a multi-agent collaboration system where multiple agents harboring divergent thoughts converge towards a common goal, ensuring reliable and successful EDA flow automation. Specifically, each agent is controlled by ChipLlama models, which are expert LLMs fine-tuned for EDA flow automation. Our experiments demonstrate the state-of-the-art (SOTA) performance of our ChipLlama models and validate the effectiveness of our EDAid in the automation of complex EDA flows, showcasing superior performance compared to single-agent systems.

OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the conventional autoregressive method of generating answers to a more deliberate approach that models the slow-thinking process through step-by-step reasoning training. Reinforcement learning plays a key role in both the model's training and decoding processes. In this article, we present a comprehensive formulation of reasoning problems and investigate the use of both model-based and model-free approaches to better support this slow-thinking framework.

The application of large language models (LLMs) in the legal domain holds significant potential for information retrieval and question answering, yet Thai legal QA systems face challenges due to a lack of standardized evaluation benchmarks and the complexity of Thai legal structures. This paper introduces NitiBench, a benchmark comprising two datasets: the NitiBench-CCL, covering general Thai financial law, and the NitiBench-Tax, which includes real-world tax law cases requiring advanced legal reasoning. We evaluate retrieval-augmented generation (RAG) and long-context LLM-based approaches to address three key research questions: the impact of domain-specific components like section-based chunking and cross-referencing, the comparative performance of different retrievers and LLMs, and the viability of long-context LLMs as an alternative to RAG. Our results show that section-based chunking significantly improves retrieval and end-to-end performance, current retrievers struggle with complex queries, and long-context LLMs still underperform RAG-based systems in Thai legal QA. To support fair evaluation, we propose tailored multi-label retrieval metrics and the use of an LLM-as-judge for coverage and contradiction detection method. These findings highlight the limitations of current Thai legal NLP solutions and provide a foundation for future research in the field. We also open-sourced our codes and dataset to available publicly.

This study investigates how large language models (LLMs) represent and recall multi-associated attributes across transformer layers. We show that intermediate layers encode factual knowledge by superimposing related attributes in overlapping spaces, along with effective recall even when attributes are not explicitly prompted. In contrast, later layers refine linguistic patterns and progressively separate attribute representations, optimizing task-specific outputs while appropriately narrowing attribute recall. We identify diverse encoding patterns including, for the first time, the observation of 3D spiral structures when exploring information related to the periodic table of elements. Our findings reveal a dynamic transition in attribute representations across layers, contributing to mechanistic interpretability and providing insights for understanding how LLMs handle complex, interrelated knowledge.

Citation faithfulness detection is critical for enhancing retrieval-augmented generation (RAG) systems, yet large-scale Chinese datasets for this task are scarce. Existing methods face prohibitive costs due to the need for manually annotated negative samples. To address this, we introduce the first large-scale Chinese dataset CiteCheck for citation faithfulness detection, constructed via a cost-effective approach using two-stage manual annotation. This method balances positive and negative samples while significantly reducing annotation expenses. CiteCheck comprises training and test splits. Experiments demonstrate that: (1) the test samples are highly challenging, with even state-of-the-art LLMs failing to achieve high accuracy; and (2) training data augmented with LLM-generated negative samples enables smaller models to attain strong performance using parameter-efficient fine-tuning. CiteCheck provides a robust foundation for advancing citation faithfulness detection in Chinese RAG systems. The dataset is publicly available to facilitate research.

This study presents the development and testing of a conversational speech system designed for robots to detect speech biomarkers indicative of cognitive impairments in people living with dementia (PLwD). The system integrates a backend Python WebSocket server and a central core module with a large language model (LLM) fine-tuned for dementia to process user input and generate robotic conversation responses in real-time in less than 1.5 seconds. The frontend user interface, a Progressive Web App (PWA), displays information and biomarker score graphs on a smartphone in real-time to human users (PLwD, caregivers, clinicians). Six speech biomarkers based on the existing literature - Altered Grammar, Pragmatic Impairments, Anomia, Disrupted Turn-Taking, Slurred Pronunciation, and Prosody Changes - were developed for the robot conversation system using two datasets, one that included conversations of PLwD with a human clinician (DementiaBank dataset) and one that included conversations of PLwD with a robot (Indiana dataset). We also created a composite speech biomarker that combined all six individual biomarkers into a single score. The speech system's performance was first evaluated on the DementiaBank dataset showing moderate correlation with MMSE scores, with the composite biomarker score outperforming individual biomarkers. Analysis of the Indiana dataset revealed higher and more variable biomarker scores, suggesting potential differences due to study populations (e.g. severity of dementia) and the conversational scenario (human-robot conversations are different from human-human). The findings underscore the need for further research on the impact of conversational scenarios on speech biomarkers and the potential clinical applications of robotic speech systems.

Reward design plays a pivotal role in the training of game AIs, requiring substantial domain-specific knowledge and human effort. In recent years, several studies have explored reward generation for training game agents and controlling robots using large language models (LLMs). In the content generation literature, there has been early work on generating reward functions for reinforcement learning agent generators. This work introduces PCGRLLM, an extended architecture based on earlier work, which employs a feedback mechanism and several reasoning-based prompt engineering techniques. We evaluate the proposed method on a story-to-reward generation task in a two-dimensional environment using two state-of-the-art LLMs, demonstrating the generalizability of our approach. Our experiments provide insightful evaluations that demonstrate the capabilities of LLMs essential for content generation tasks. The results highlight significant performance improvements of 415% and 40% respectively, depending on the zero-shot capabilities of the language model. Our work demonstrates the potential to reduce human dependency in game AI development, while supporting and enhancing creative processes.

Dynamic Text-Attributed Graphs (DyTAGs) have numerous real-world applications, e.g. social, collaboration, citation, communication, and review networks. In these networks, nodes and edges often contain text descriptions, and the graph structure can evolve over time. Future link prediction, edge classification, relation generation, and other downstream tasks on DyTAGs require powerful representations that encode structural, temporal, and textual information. Although graph neural networks (GNNs) excel at handling structured data, encoding temporal information within dynamic graphs remains a significant challenge. In this work, we propose LLM-driven Knowledge Distillation for Dynamic Text Attributed Graph (LKD4DyTAG) with temporal encoding to address these challenges. We use a simple, yet effective approach to encode temporal information in edges so that graph convolution can simultaneously capture both temporal and structural information in the hidden representations. To leverage LLM's text processing capabilities for learning richer representations on DyTAGs, we distill knowledge from LLM-driven edge representations (based on a neighborhood's text attributes) into saptio-temporal representations using a lightweight GNN model that encodes temporal and structural information. The objective of knowledge distillation enables the GNN to learn representations that more effectively encode the available structural, temporal, and textual information in DyTAG. We conducted extensive experimentation on six real-world DyTAG datasets to verify the effectiveness of our approach LKD4DyTAG for future link prediction and edge classification task. The results show that our approach significantly improves the performance of downstream tasks compared to the baseline models.

In this paper, we first present a novel way of computationally analysing and extracting illocutionary forces from dialogue using Bert-based Large Language Models, and demonstrate how these features impact the response of a conversational agent guided by a document-based knowledge bank demonstrated by a bespoke web conversational chat agent system developed. Our proposed illocutionary force extraction and classification technique is the first of its kind using the Argument Interchange Format (AIF) Dataset, showing an improved performance compared to two methods for carrying out similar tasks with a macro F1 of approximately 45%. When we evaluated the system based on 2 knowledge files, with 2 user queries each, across 5 open-source large language models (LLMs) using 10 standard metrics we found out that larger open-source models, such as Llama2:13b and Llama3-chatqa-latest, demonstrated an improved alignment when the user illocutionary force was included with their query, achieving higher QA and linguistic similarity scores. The smaller models on the other hand like Tinyllama:latest showed an increased perplexity and mixed performance, which explicitly indicated struggles in processing queries that explicitly included illocutionary forces. The results from the analysis highlight the potential of illocutionary force to enhance conversational depth while underscoring the need for model-specific optimizations to address increased computational costs and response times.

Self-attention is essential to Transformer architectures, yet how information is embedded in the self-attention matrices and how different objective functions impact this process remains unclear. We present a mathematical framework to analyze self-attention matrices by deriving the structures governing their weight updates. Using this framework, we demonstrate that bidirectional training induces symmetry in the weight matrices, while autoregressive training results in directionality and column dominance. Our theoretical findings are validated across multiple Transformer models - including ModernBERT, GPT, LLaMA3, and Mistral - and input modalities like text, vision, and audio. Finally, we apply these insights by showing that symmetric initialization improves the performance of encoder-only models on language tasks. This mathematical analysis offers a novel theoretical perspective on how information is embedded through self-attention, thereby improving the interpretability of Transformer models.