Cover Image

Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Xiyang, Li, Zongxia, Shi, Guangyao, Duffy, Alexander, Marques, Tyler, Olson, Matthew Lyle, Zhou, Tianyi, Manocha, Dinesh
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models
by: Wu, Xiyang, et al.
Published: (2026)

Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning
by: Yan, John, et al.
Published: (2026)

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding
by: Li, Zongxia, et al.
Published: (2025)

EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks
by: Feng, Tongtong, et al.
Published: (2025)

MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models
by: Wu, Xiyang, et al.
Published: (2025)

Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
by: Liu, Dawei, et al.
Published: (2026)

A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges
by: Li, Zongxia, et al.
Published: (2025)

Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
by: Yang, Cheng, et al.
Published: (2025)

Counterfactual Trace Auditing of LLM Agent Skills
by: Zhou, Xiaolin, et al.
Published: (2026)

Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy
by: Duffy, Alexander, et al.
Published: (2025)

HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models
by: Guan, Tianrui, et al.
Published: (2023)

PACE: Data-Driven Virtual Agent Interaction in Dense and Cluttered Environments
by: Mullen, James, et al.
Published: (2023)

HawkI: Homography & Mutual Information Guidance for 3D-free Single Image to Aerial View
by: Kothandaraman, Divya, et al.
Published: (2023)

CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification
by: Zhang, Hanrong, et al.
Published: (2026)

LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks
by: Chandwani, Abhishek, et al.
Published: (2026)

MemCtrl: Using MLLMs as Active Memory Controllers on Embodied Agents
by: Dorbala, Vishnu Sashank, et al.
Published: (2026)

DeCo: Task Decomposition and Skill Composition for Zero-Shot Generalization in Long-Horizon 3D Manipulation
by: Chen, Zixuan, et al.
Published: (2025)

DocuBits: VR Document Decomposition for Procedural Task Completion
by: Lee, Geonsun, et al.
Published: (2024)

HorizonBench: Long-Horizon Personalization with Evolving Preferences
by: Li, Shuyue Stella, et al.
Published: (2026)

PolicyBank: Evolving Policy Understanding for LLM Agents
by: Choi, Jihye, et al.
Published: (2026)

COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context
by: Wan, Guangya, et al.
Published: (2025)

AG-CVG: Coverage Planning with a Mobile Recharging UGV and an Energy-Constrained UAV
by: Karapetyan, Nare, et al.
Published: (2023)

LBAP: Improved Uncertainty Alignment of LLM Planners using Bayesian Inference
by: Mullen Jr., James F., et al.
Published: (2024)

SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents
by: Hu, Wentao, et al.
Published: (2026)

Speech2UnifiedExpressions: Synchronous Synthesis of Co-Speech Affective Face and Body Expressions from Affordable Inputs
by: Bhattacharya, Uttaran, et al.
Published: (2024)

WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents
by: Liu, Junteng, et al.
Published: (2025)

FALCON: Future-Aware Learning with Contextual Object-Centric Pretraining for UAV Action Recognition
by: Xian, Ruiqi, et al.
Published: (2024)

Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigation
by: Dorbala, Vishnu Sashank, et al.
Published: (2023)

GTA: Generating Long-Horizon Tasks for Web Agents at Scale
by: Huang, Tenghao, et al.
Published: (2026)

Structured Uncertainty guided Clarification for LLM Agents
by: Suri, Manan, et al.
Published: (2025)

O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents
by: Wang, Piaohong, et al.
Published: (2025)

SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks
by: Wen, Yongyan, et al.
Published: (2024)

First Frame Is the Place to Go for Video Content Customization
by: Chen, Jingxi, et al.
Published: (2025)

Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces
by: Chowdhury, Sanjoy, et al.
Published: (2026)

Listen2Scene: Interactive material-aware binaural sound propagation for reconstructed 3D scenes
by: Ratnarajah, Anton, et al.
Published: (2023)

Inst4DGS: Instance-Decomposed 4D Gaussian Splatting with Multi-Video Label Permutation Learning
by: Lee, Yonghan, et al.
Published: (2026)

EM-GANSim: Real-time and Accurate EM Simulation Using Conditional GANs for 3D Indoor Scenes
by: Wang, Ruichen, et al.
Published: (2024)

MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents
by: Zhang, Haozhen, et al.
Published: (2026)

TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification
by: Anand, Nishit, et al.
Published: (2024)

SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks
by: Hu, Jinchao, et al.
Published: (2026)