Paper Summaries

Paper citation: Chen, Weize, Jiarui Yuan, Chen Qian, Cheng Yang, Zhiyuan Liu, and Maosong Sun. “Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System.” arXiv preprint arXiv:2410.08115 (2024). Summary In the rapidly evolving realm of AI, large language models (LLMs) are gaining traction for their role in multi-agent systems (MAS), where multiple AI agents collaborate…

Summary In recent years, AI safety mechanisms have become more sophisticated in training large language models (LLMs) to refuse requests for harmful content, with the aim of preventing adverse societal impacts such as misinformation and violence.  However, the authors identify a significant vulnerability in these safety systems through their innovative methodology, MathPrompt, which transforms harmful…

paper citation: Zhao, Siyun, Yuqing Yang, Zilong Wang, Zhiyuan He, Luna K. Qiu, and Lili Qiu. “Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely.” arXiv preprint arXiv:2409.14924 (2024). Summary The research presents a detailed examination of how large language models (LLMs) can be…

paper citation: Zhang, Yifan, Yang Yuan, and Andrew Chi-Chih Yao. “On the Diagram of Thought.” arXiv preprint arXiv:2409.10038 (2024). Summary The Diagram of Thought (DoT) framework proposes a novel method for enhancing the reasoning capabilities of large language models (LLMs) by utilizing a directed acyclic graph (DAG) that incorporates an iterative workflow.  Unlike traditional linear…

Paper citation: Radha, Santosh Kumar, Yasamin Nouri Jelyani, Ara Ghukasyan, and Oktay Goktas. “Iteration of Thought: Leveraging Inner Dialogue for Autonomous Large Language Model Reasoning.” arXiv preprint arXiv:2409.12618 (2024). Summary The Iteration of Thought (IoT) framework leverages the advanced processing capabilities of large language models (LLMs) by employing an Inner Dialogue Agent (IDA) that generates…

Paper citation: Valmeekam, Karthik, Kaya Stechly, and Subbarao Kambhampati. “LLMs Still Can’t Plan; Can LRMs? A Preliminary Evaluation of OpenAI’s o1 on PlanBench.” arXiv preprint arXiv:2409.13373 (2024). Summary: The research investigates the distinction between traditional LLMs, which rely heavily on approximate retrieval, and OpenAI’s latest offering, the O1 model, characterized as a Large Reasoning Model…

arXiv, 2024 Paper citation: Deitke, Matt, Christopher Clark, Sangho Lee, Rohun Tripathi, Yue Yang, Jae Sung Park, Mohammadreza Salehi et al. “Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models.” arXiv preprint arXiv:2409.17146 (2024). Two Sentence Summary Dataset Performance Approach Implementation Components Data Collection: Model Training: Python Code for Molmo Algorithm Step 1:…