paper-with-me

홈 › Papers

Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution

2025-05-26 · Jiahao Qiu, Xuan Qi, Tongcheng Zhang, Xinzhe Juan, Jiacheng Guo, Yifu Lu, Yimin Wang, Zixin Yao, Qihan Ren, Xun Jiang, Xing Zhou, Dongrui Liu, Ling Yang, Yue Wu, Kaixuan Huang, Shilong Liu, Hongru Wang, Mengdi Wang

Recent advances in large language models (LLMs) have enabled agents to autonomously perform complex, open-ended tasks. However, many existing frameworks depend heavily on manually predefined tools and workflows, which hinder their adaptability, scalability, and generalization across domains. In this work, we introduce Alita--a generalist agent designed with the principle of "Simplicity is the ultimate sophistication," enabling scalable agentic reasoning through minimal predefinition and maximal self-evolution. For minimal predefinition, Alita is equipped with only one component for direct problem-solving, making it much simpler and neater than previous approaches that relied heavily on hand-crafted, elaborate tools and workflows. This clean design enhances its potential to generalize to challenging questions, without being limited by tools. For Maximal self-evolution, we enable the creativity of Alita by providing a suite of general-purpose components to autonomously construct, refine, and reuse external capabilities by generating task-related model context protocols (MCPs) from open source, which contributes to scalable agentic reasoning. Notably, Alita achieves 75.15% pass@1 and 87.27% pass@3 accuracy, which is top-ranking among general-purpose agents, on the GAIA benchmark validation dataset, 74.00% and 52.00% pass@1, respectively, on Mathvista and PathVQA, outperforming many agent systems with far greater complexity. More details will be updated at $\href{https://github.com/CharlesQ9/Alita}{https://github.com/CharlesQ9/Alita}$.

📄 PDF Abstract BibTeX arXiv:2505.20286

Code (1)

charlesq9/alita 공식 구현

Similar Papers 제목 키워드 기반

AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework

2025-10-05 · Hanchen Zhang, Xiao Liu, Bowen Lv, Xueqiao Sun 외 arxiv

Recent advances in large language models (LLMs) have sparked growing interest in building generalist agents that can learn through online interactions. However, applying reinforcement learning (RL) to train LLM agents in…

Reinforcement Learning

Retrieval Augmented Generation for Topic Modeling in Organizational Research: An Introduction with Empirical Demonstration

2025-02-28 · Gerion Spielberger, Florian M. Artinger, Jochen Reb, Rudolf Kerschreiter

Analyzing textual data is the cornerstone of qualitative research. While traditional methods such as grounded theory and content analysis are widely used, they are labor-intensive and time-consuming. Topic modeling offer…

RAGRetrievalRetrieval-augmented Generation

TxGemma: Efficient and Agentic LLMs for Therapeutics

2025-04-08 · Eric Wang, Samuel Schmidgall, Paul F. Jaeger, Fan Zhang 외

Therapeutic development is a costly and high-risk endeavor that is often plagued by high failure rates. To address this, we introduce TxGemma, a suite of efficient, generalist large language models (LLMs) capable of ther…

Humanity's Last ExamProperty Prediction

Orchestrator-Agent Trust: A Modular Agentic AI Visual Classification System with Trust-Aware Orchestration and RAG-Based Reasoning

2025-07-09 · Konstantinos I. Roumeliotis, Ranjan Sapkota, Manoj Karkee, Nikolaos D. Tselikas

Modern Artificial Intelligence (AI) increasingly relies on multi-agent architectures that blend visual and language understanding. Yet, a pressing challenge remains: How can we trust these agents especially in zero-shot …

BenchmarkingImage RetrievalOptical Character Recognition (OCR)RAG+3

AstroReason-Bench: Evaluating Unified Agentic Planning across Heterogeneous Space Planning Problems

2026-01-16 · Weiyi Wang, Xinchi Chen, Jingjing Gong, Xuanjing Huang 외 arxiv

Recent advances in agentic Large Language Models (LLMs) have positioned them as generalist planners capable of reasoning and acting across diverse tasks. However, existing agent benchmarks largely focus on symbolic or we…