Cover Image

Continual Harness: Online Adaptation for Self-Improving Foundation Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Karten, Seth, Zhang, Joel, Upaa Jr, Tersoo, Feng, Ruirong, Li, Wenzhe, Shi, Chengshuai, Jin, Chi, Vodrahalli, Kiran
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
by: Li, Wenzhe, et al.
Published: (2024)

Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning
by: Shi, Chengshuai, et al.
Published: (2026)

The PokeAgent Challenge: Competitive and Long-Context Learning at Scale
by: Karten, Seth, et al.
Published: (2026)

Automatic Generation of High-Performance RL Environments
by: Karten, Seth, et al.
Published: (2026)

Dynamic Continual Learning: Harnessing Parameter Uncertainty for Improved Network Adaptation
by: Angelini, Christopher, et al.
Published: (2025)

Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces
by: Karten, Seth, et al.
Published: (2026)

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
by: Lin, Minhua, et al.
Published: (2026)

Next-Token Prediction and Regret Minimization
by: Mohri, Mehryar, et al.
Published: (2026)

Online Learning with Bounded Recall
by: Schneider, Jon, et al.
Published: (2022)

LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra
by: Karten, Seth, et al.
Published: (2025)

Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents
by: Xu, Tianshi, et al.
Published: (2026)

Continual Learning, Not Training: Online Adaptation For Agents
by: Jaglan, Aman, et al.
Published: (2025)

PokéChamp: an Expert-level Minimax Language Agent
by: Karten, Seth, et al.
Published: (2025)

EvoMem: Improving Multi-Agent Planning with Dual-Evolving Memory
by: Fan, Wenzhe, et al.
Published: (2025)

ArtWhisperer: A Dataset for Characterizing Human-AI Interactions in Artistic Creations
by: Vodrahalli, Kailas, et al.
Published: (2023)

On The Statistical Limits of Self-Improving Agents
by: Wang, Charles L., et al.
Published: (2025)

Learning a Canonical Basis of Human Preferences from Binary Ratings
by: Vodrahalli, Kailas, et al.
Published: (2025)

AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents
by: Zhong, Hailin, et al.
Published: (2026)

SIDiffAgent: Self-Improving Diffusion Agent
by: Garg, Shivank, et al.
Published: (2026)

Self-adapting Robotic Agents through Online Continual Reinforcement Learning with World Model Feedback
by: Domberg, Fabian, et al.
Published: (2026)

STGDPM:Vessel Trajectory Prediction with Spatio-Temporal Graph Diffusion Probabilistic Model
by: Wenzhe, Jin, et al.
Published: (2025)

SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation
by: Vetcha, Nitin, et al.
Published: (2026)

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation
by: Yu, Ye, et al.
Published: (2026)

General Modular Harness for LLM Agents in Multi-Turn Gaming Environments
by: Zhang, Yuxuan, et al.
Published: (2025)

A Self-Improving Coding Agent
by: Robeyns, Maxime, et al.
Published: (2025)

Multi-Agent Evolve: LLM Self-Improve through Co-evolution
by: Chen, Yixing, et al.
Published: (2025)

Harnessing Pre-Resolution Signals for Future Prediction Agents
by: Wei, Chuyang, et al.
Published: (2026)

Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing
by: Yue, Yuguang, et al.
Published: (2026)

Harnessing LLM Agents with Skill Programs
by: Liu, Hongjun, et al.
Published: (2026)

Code as Agent Harness
by: Ning, Xuying, et al.
Published: (2026)

Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows
by: Yao, Yilun, et al.
Published: (2026)

JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptation
by: Nekoei, Hadi, et al.
Published: (2025)

Efficient Continual Adaptation of Pretrained Robotic Policy with Online Meta-Learned Adapters
by: Zhu, Ruiqi, et al.
Published: (2025)

Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses
by: Jiang, Pengcheng, et al.
Published: (2026)

Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors
by: Nie, Fan, et al.
Published: (2025)

Greedy Sampling Is Provably Efficient for RLHF
by: Wu, Di, et al.
Published: (2025)

$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses
by: Wu, Di, et al.
Published: (2026)

Bilingual Adaptation of Monolingual Foundation Models
by: Gosal, Gurpreet, et al.
Published: (2024)

Architectural Design Decisions in AI Agent Harnesses
by: Wei, Hu
Published: (2026)

Efficient Multi-objective Prompt Optimization via Pure-exploration Bandits
by: Li, Donghao, et al.
Published: (2026)