Knowledge Model • Large Language Models as Planning Domain Generators • Chain of Thoughtlessness: An Analysis of CoT in Planning • Sub-goal Distillation: A Method to Improve Small Language Agents • Testing and Understanding Erroneous Planning in LLM Agents through Synthesized User Inputs ペルソナ • From Persona to Personalization: A Survey on Role-Playing Language Agents ⾃⼰修正 • Self-Reflection in LLM Agents: Effects on Problem-Solving Performance ⻑いコンテキスト理解 • Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context • Many-Shot In-Context Learning in Multimodal Foundation Models • In-Context Learning with Long-Context Models: An In-Depth Exploration • Many-Shot In-Context Learning • CinePile: A Long Video Question Answering Dataset and Benchmark RAG • A Survey on Retrieval-Augmented Text Generation for Large Language Models • When to Retrieve: Teaching LLMs to Utilize Information Retrieval Effectively
A Social Cognition View • Elements of World Knowledge (EWOK): A cognition-inspired framework for evaluating basic world knowledge in language models • Hallucination of Multimodal Large Language Models: A Survey • A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI • Large Language Models Meet NLP: A Survey Agent Framework • Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents • Human-Centered LLM-Agent User Interface: A Position Paper • How Far Are We From AGI? • Towards Guaranteed Safe AI:A Framework for Ensuring Robust and Reliable AI Systems • Air Gap: Protecting Privacy-Conscious Conversational Agents • Offline Training of Language Model Agents with Functions as Learnable Weights • Deconstructing Human-AI Collaboration: Agency, Interaction, and Adaptation • A Survey on Self-Evolution of Large Language Models • The Ethics of Advanced AI Assistants
Large Language Models • Assessing and Verifying Task Utility in LLM-Powered Applications • A Unified Industrial Large Knowledge Model Framework in Smart Manufacturing • SWE-AGENT: AGENT-COMPUTER INTERFACES ENABLE AUTOMATED SOFTWARE ENGINEERING • Automating the Enterprise with Foundation Models • Autonomous LLM-driven research from data to human-verifiable research papers Multi Agent Systems • Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Texts • MapCoder: Multi-Agent Code Generation for Competitive Problem Solving • AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments • Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents • MARE: Multi-Agents Collaboration Framework for Requirements Engineering Computer Controlled Agents • Unveiling Disparities in Web Task Handling Between Human and Web Agent • Latent State Estimation Helps UI Agents to Reason