Image de couverture de livre

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Zewen, Shi, Zhan, Sang, Yisi, He, Bing, Lin, Minhua, Wei, Tianxin, Wang, Dakuo, Dumoulin, Benoit, Jin, Wei, Lu, Hanqing
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents
par: Lin, Minhua, et autres
Publié: (2026)

Position: Agentic Evolution is the Path to Evolving LLMs
par: Lin, Minhua, et autres
Publié: (2026)

Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs
par: Lu, Yuxuan, et autres
Publié: (2026)

Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing
par: Weng, Zhaotian, et autres
Publié: (2026)

Safety Must Precede the Deployment of Open-Ended AI
par: Sheth, Ivaxi, et autres
Publié: (2025)

JaxLife: An Open-Ended Agentic Simulator
par: Lu, Chris, et autres
Publié: (2024)

TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking
par: Zeng, Churui, et autres
Publié: (2026)

JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks
par: Lin, Lanbo, et autres
Publié: (2026)

SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
par: Kwan, Wai-Chung, et autres
Publié: (2026)

Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning
par: Ye, Zhiling, et autres
Publié: (2025)

Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation
par: Zhao, Zhonghan, et autres
Publié: (2024)

OpenSIR: Open-Ended Self-Improving Reasoner
par: Kwan, Wai-Chung, et autres
Publié: (2025)

AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting
par: Zhou, Xiaoyu, et autres
Publié: (2025)

MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
par: Zhang, Kai, et autres
Publié: (2024)

Open-Ended Task Discovery via Bayesian Optimization
par: Adachi, Masaki, et autres
Publié: (2026)

Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents
par: Wang, Ziyi, et autres
Publié: (2026)

AutoLibra: Agent Metric Induction from Open-Ended Human Feedback
par: Zhu, Hao, et autres
Publié: (2025)

TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
par: He, Pengfei, et autres
Publié: (2025)

Ranking Distillation for Open-Ended Video Question Answering with Insufficient Labels
par: Liang, Tianming, et autres
Publié: (2024)

RewardHarness: Self-Evolving Agentic Post-Training
par: Zhang, Yuxuan, et autres
Publié: (2026)

Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
par: Tian, Jinchuan, et autres
Publié: (2026)

InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training
par: Wang, Pengkai, et autres
Publié: (2025)

Seeing but Not Believing: Probing the Disconnect Between Visual Attention and Answer Correctness in VLMs
par: Liu, Zhining, et autres
Publié: (2025)

G-Zero: Self-Play for Open-Ended Generation from Zero Data
par: Huang, Chengsong, et autres
Publié: (2026)

Open-Ended Video Game Glitch Detection with Agentic Reasoning and Temporal Grounding
par: Zheng, Muyang, et autres
Publié: (2026)

Data-Efficient Stream-Based Active Distillation for Scalable Edge Model Deployment
par: Manjah, Dani, et autres
Publié: (2025)

AutoTailor: Automatic and Efficient Adaptive Model Deployment for Diverse Edge Devices
par: Liu, Mengyang, et autres
Publié: (2025)

Adaptive Self-Improvement for Smarter Energy Systems using Agentic Policy Search
par: Sommer, Alexander, et autres
Publié: (2025)

Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks
par: Jiang, Chunyang, et autres
Publié: (2025)

Improving Open-Ended Text Generation via Adaptive Decoding
par: Zhu, Wenhong, et autres
Publié: (2024)

O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL
par: Yao, Yi, et autres
Publié: (2026)

SToLa: Self-Adaptive Touch-Language Framework with Tactile Commonsense Reasoning in Open-Ended Scenarios
par: Cheng, Ning, et autres
Publié: (2025)

CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks
par: Besta, Maciej, et autres
Publié: (2024)

Features as Rewards: Scalable Supervision for Open-Ended Tasks via Interpretability
par: Prasad, Aaditya Vikram, et autres
Publié: (2026)

On Creativity and Open-Endedness
par: Soros, L. B., et autres
Publié: (2024)

StyleStream: Real-Time Zero-Shot Voice Style Conversion
par: Liu, Yisi, et autres
Publié: (2026)

Reverse-Engineered Reasoning for Open-Ended Generation
par: Wang, Haozhe, et autres
Publié: (2025)

Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity
par: Costales, Robby, et autres
Publié: (2024)

$A^2Flow:$ Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators
par: Zhao, Mingming, et autres
Publié: (2025)

Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators
par: Wang, Chengcheng, et autres
Publié: (2026)