공대생 도전 일지

https://arxiv.org/abs/2402.17574 Agent-Pro: Learning to Evolve via Policy-Level Reflection and OptimizationLarge Language Models (LLMs) exhibit robust problem-solving capabilities for diverse tasks. However, most LLM-based agents are designed as specific task solvers with sophisticated prompt engineering, rather than agents capable of learning and evolving throarxiv.org 여태까지는 한 판의 게임을 어떻게 이길까, 목..

https://arxiv.org/abs/2309.07870이 논문은 LLM의 한계를 넘기 위해 다양한 방법을 사용했습니다.Agent는 LLM의 능력을 오로지 쓴다기 보다는 장, 단기 기억을 LLM혹은 BERT류를 통해 저장하고, 상태에 따라 다양한 API를 쓰면서 다중 에이전트를 통해 토론 및 동적인 스케쥴링을 진행하여 LLM의 기능을 강화했습니다.이러한 메모리와 API활용을 통해 LLM의 능력을 더 활용하였고, 새로운 시스템을 활용할 수 있도록 프레임워크도 개방하였습니다. 항목내용논문 제목AGENTS: An Open-source Framework for Autonomous Language Agents주요 목표- LLM의 한계를 보완하여 더 복잡한 작업을 수행할 수 있는 에이전트 시스템 설계- 연구자, ..

DEPS2024.11.27 - [인공지능/논문 리뷰 or 진행] - Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents - 논문 리뷰 Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents - 논https://arxiv.org/abs/2302.01560 Describe, Explain, Plan and Select: Interactive Planning with Large Langua..

https://arxiv.org/abs/2302.01560 Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task AgentsWe investigate the challenge of task planning for multi-task embodied agents in open-world environments. Two main difficulties are identified: 1) executing plans in an open-world environment (e.g., Minecraft) necessitates accurate and multi-step..

https://arxiv.org/abs/2304.11477 LLM+P: Empowering Large Language Models with Optimal Planning ProficiencyLarge language models (LLMs) have demonstrated remarkable zero-shot generalization abilities: state-of-the-art chatbots can provide plausible answers to many common questions that arise in daily life. However, so far, LLMs cannot reliably solve long-horizoarxiv.org 로봇을 조종하는 LLM 모델이네요. 장기 계획을..

https://arxiv.org/abs/2310.04406 Language Agent Tree Search Unifies Reasoning Acting and Planning in Language ModelsWhile language models (LMs) have shown potential across a range of decision-making tasks, their reliance on simple acting processes limits their broad deployment as autonomous agents. In this paper, we introduce Language Agent Tree Search (LATS) -- the firarxiv.org 이 논문은 강화학습의 MCTS..

https://arxiv.org/abs/2309.13007 ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMsLarge Language Models (LLMs) still struggle with natural language reasoning tasks. Motivated by the society of minds (Minsky, 1988), we propose ReConcile, a multi-model multi-agent framework designed as a round table conference among diverse LLM agents. Rearxiv.org 기존 LLM은 새로운 생각..

https://arxiv.org/abs/2305.17144 Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based KnowledgeThe captivating realm of Minecraft has attracted substantial research interest in recent years, serving as a rich platform for developing intelligent agents capable of functioning in open-world environments. However, the current research..

https://arxiv.org/abs/2308.10144 ExpeL: LLM Agents Are Experiential LearnersThe recent surge in research interest in applying large language models (LLMs) to decision-making tasks has flourished by leveraging the extensive world knowledge embedded in LLMs. While there is a growing demand to tailor LLMs for custom decision-making tarxiv.org  이 논문도 LLM이 새로운 정보에 대해 어떻게 저장하거나 사용할지에 대한 논문입니다.문제: LLM을..

https://arxiv.org/abs/2305.16843 Randomized Positional Encodings Boost Length Generalization of TransformersTransformers have impressive generalization capabilities on tasks with a fixed context length. However, they fail to generalize to sequences of arbitrary length, even for seemingly simple tasks such as duplicating a string. Moreover, simply training on lonarxiv.org 학습 혹은 추론 때 토큰 길이에 대한 논문이..