Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Qiu, Jiahao, Qi, Xuan, Zhang, Tongcheng, Juan, Xinzhe, Guo, Jiacheng, Lu, Yifu, Wang, Yimin, Yao, Zixin, Ren, Qihan, Jiang, Xun, Zhou, Xing, Liu, Dongrui, Yang, Ling, Wu, Yue, Huang, Kaixuan, Liu, Shilong, Wang, Hongru, Wang, Mengdi
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Alita-G: Self-Evolving Generative Agent for Agent Generation
par: Qiu, Jiahao, et autres
Publié: (2025)

AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes
par: Qiu, Jiahao, et autres
Publié: (2025)

Learning Agent Routing From Early Experience
par: Wang, Yimin, et autres
Publié: (2026)

EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safety
par: Qiu, Jiahao, et autres
Publié: (2025)

Physics Supernova: AI Agent Matches Elite Gold Medalists at IPhO 2025
par: Qiu, Jiahao, et autres
Publié: (2025)

Temporal Consistency for LLM Reasoning Process Error Identification
par: Guo, Jiacheng, et autres
Publié: (2025)

Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?
par: Qi, Xuan, et autres
Publié: (2025)

TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling
par: Qiu, Jiahao, et autres
Publié: (2024)

GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators
par: Guo, Jiacheng, et autres
Publié: (2025)

Web World Models
par: Feng, Jichen, et autres
Publié: (2025)

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
par: Gao, Huan-ang, et autres
Publié: (2025)

SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
par: Huang, Kaixuan, et autres
Publié: (2024)

Iterative Thresholding Methods for Longest Minimal Length Partitions
par: Hu, Shilong, et autres
Publié: (2024)

Avenir-Web: Human-Experience-Imitating Multimodal Web Agents with Mixture of Grounding Experts
par: Li, Aiden Yiliu, et autres
Publié: (2026)

On the Role of Preference Variance in Preference Optimization
par: Guo, Jiacheng, et autres
Publié: (2025)

Preacher: Paper-to-Video Agentic System
par: Liu, Jingwei, et autres
Publié: (2025)

The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
par: Qian, Chen, et autres
Publié: (2026)

A Theoretical Perspective for Speculative Decoding Algorithm
par: Yin, Ming, et autres
Publié: (2024)

CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations
par: Gao, Huan-ang, et autres
Publié: (2025)

The incorporation of KF‐6017 and LiTFSI benefiting for constructing a transparent, highly conductive polydimethylsiloxane‐based ionogel with high‐ionic liquid content
par: Wei Liu, et autres
Publié: (2024)

Improving the Transferability of Adversarial Attacks by an Input Transpose
par: Wan, Qing, et autres
Publié: (2025)

Diffusion Model as a Generalist Segmentation Learner
par: Wang, Haoxiao, et autres
Publié: (2026)

OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards
par: Li, Zehao, et autres
Publié: (2026)

Comment and Control: Hijacking Agentic Workflows via Context-Grounded Evolution
par: Fendley, Neil, et autres
Publié: (2026)

Randomness in appendage coordination facilitates strenuous ground self-righting
par: Xuan, Qihan, et autres
Publié: (2020)

Environmental force sensing helps robots traverse cluttered large obstacles using physical interaction
par: Xuan, Qihan, et autres
Publié: (2021)

Coordinated appendages accumulate more energy to self-right on the ground
par: Xuan, Qihan, et autres
Publié: (2020)

Towards the Dynamics of a DNN Learning Symbolic Interactions
par: Ren, Qihan, et autres
Publié: (2024)

SEGMN: A Structure-Enhanced Graph Matching Network for Graph Similarity Learning
par: Wang, Wenjun, et autres
Publié: (2024)

T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs
par: Li, Siyang, et autres
Publié: (2024)

CLEAN-MI: A Scalable and Efficient Pipeline for Constructing High-Quality Neurodata in Motor Imagery Paradigm
par: Liu, Dingkun, et autres
Publié: (2025)

Heterogeneous Influence Maximization in User Recommendation
par: Hou, Hongru, et autres
Publié: (2025)

Locomotor transitions in the potential energy landscape-dominated regime
par: Othayoth, Ratan, et autres
Publié: (2021)

CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency
par: Guo, Jiacheng, et autres
Publié: (2025)

CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning
par: Wang, Mengdi, et autres
Publié: (2025)

Diffusion Model for Manifold Data: Score Decomposition, Curvature, and Statistical Complexity
par: Zhang, Zixuan, et autres
Publié: (2026)

Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents
par: Wang, Zihao, et autres
Publié: (2025)

Pressure‐Dependent Anisotropic Elastic Properties of Cracked Artificial Shale With Varying Crack and Background Porosity
par: Tongcheng Han, et autres
Publié: (2026)

Position: Agent Should Invoke External Tools ONLY When Epistemically Necessary
par: Wang, Hongru, et autres
Publié: (2025)

Vision Generalist Model: A Survey
par: Wang, Ziyi, et autres
Publié: (2025)