공대생 도전 일지

https://arxiv.org/abs/2401.17167 Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex ScenariosThe recent trend of using Large Language Models (LLMs) as tool agents in real-world applications underscores the necessity for comprehensive evaluations of their capabilities, particularly in complex scenarios involving planning, creating, and using tool..

https://github.com/Shiguang-Guo/Open-Grounded-Planning GitHub - Shiguang-Guo/Open-Grounded-PlanningContribute to Shiguang-Guo/Open-Grounded-Planning development by creating an account on GitHub.github.com https://arxiv.org/abs/2406.02903 Open Grounded Planning: Challenges and Benchmark ConstructionThe emergence of large language models (LLMs) has increasingly drawn attention to the use of LLMs f..

https://arxiv.org/abs/2206.10498 PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about ChangeGenerating plans of action, and reasoning about change have long been considered a core competence of intelligent agents. It is thus no surprise that evaluating the planning and reasoning capabilities of large language models (LLMs) has become a hot topic..

https://arxiv.org/abs/2311.05772 LLM을 Agent로 사용하는 방식엔 크게 두 가지이다.1. 다음 작업을 반복적으로 결정2. LLM을 통해 계획 생성, 하위 작업을 실행그러나 이러한 방법들은 하위 작업들을 실패하면 작업이 실패해 버린다-> 계획을 실행할 수 없는 경우 다시 재귀적으로 분해하여 문제를 해결하는 As-Needed Decomposition And Planning for complex Tasks(ADaPT)를 제안한다. 이 이미지가 너무 명확하게 ADaPT를 설명해줍니다.Excutor에게는 간결한 언어 작업 사양이 제공됩니다. LLM을 통해 Action을 진행하고, 환경과 반복적으로 상호작용하며 완료되거나, 설정된 최대 반복 제한까지 계속됩니다. Task를 원자 수준의..

https://arxiv.org/abs/2305.16653 AdaPlanner: Adaptive Planning from Feedback with Language ModelsLarge language models (LLMs) have recently demonstrated the potential in acting as autonomous agents for sequential decision-making tasks. However, most existing methods either take actions greedily without planning or rely on static plans that are not adaarxiv.org Planner - 작은 단위의 목표로 나누고, 각 목표를 달성하..

https://arxiv.org/abs/2405.16510 Planning with Multi-Constraints via Collaborative Language AgentsThe rapid advancement of neural language models has sparked a new surge of intelligent agent research. Unlike traditional agents, large language model-based agents (LLM agents) have emerged as a promising paradigm for achieving artificial general intelligearxiv.org 여러 제약 조건이 있는 복잡한 작업 계획에 대해 실행 가능하거..

https://arxiv.org/abs/2305.04091 Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language ModelsLarge language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. To tackle multi-step reasoning tasks, few-shot chain-of-thought (CoT) prompting includes a few manually crafted step-by-step reasoning demonstratiarxiv.org 드디..

https://arxiv.org/abs/2403.03101 KnowAgent: Knowledge-Augmented Planning for LLM-Based AgentsLarge Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges, especially when interacting with environments through generating executable actions. This inadequacyarxiv.org https://zjunlp.github.io/project/KnowAg..

https://arxiv.org/abs/2402.02716 Understanding the planning of LLM agents: A surveyAs Large Language Models (LLMs) have shown significant intelligence, the progress to leverage LLMs as planning modules of autonomous agents has attracted more attention. This survey provides the first systematic view of LLM-based agents planning, coveringarxiv.org 첫 번째 Planning Survey논문이라네요Task Decomposition은 분할 정..

https://arxiv.org/abs/2410.00467 Dynamic Planning for LLM-based Graphical User Interface AutomationThe advent of large language models (LLMs) has spurred considerable interest in advancing autonomous LLMs-based agents, particularly in intriguing applications within smartphone graphical user interfaces (GUIs). When presented with a task goal, these agentarxiv.org 기존 ReAct방식은 너무 길어져서 GUI Agent나 현실..