Image de couverture de livre

Actively Obtaining Environmental Feedback for Autonomous Action Evaluation Without Predefined Measurements

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Su, Hong
Format:	Preprint
Publié:	2026
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

Autonomous Question Formation for Large Language Model-Driven AI Systems
par: Su, Hong
Publié: (2026)

Active Thinking Model: A Goal-Directed Self-Improving Framework for Real-World Adaptive Intelligence
par: Su, Hong
Publié: (2025)

Predefined Prototypes for Intra-Class Separation and Disentanglement
par: Almudévar, Antonio, et autres
Publié: (2024)

An LLM-Driven Closed-Loop Autonomous Learning Framework for Robots Facing Uncovered Tasks in Open Environments
par: Su, Hong
Publié: (2026)

Simulating Human Cognition: Heartbeat-Driven Autonomous Thinking Activity Scheduling for LLM-based AI systems
par: Su, Hong
Publié: (2026)

AlgoPilot: Fully Autonomous Program Synthesis Without Human-Written Programs
par: Yin, Xiaoxin
Publié: (2025)

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
par: Wu, Lingxuan, et autres
Publié: (2024)

Variance-Bounded Evaluation of Entity-Centric AI Systems Without Ground Truth: Theory and Measurement
par: Ding, Kaihua
Publié: (2025)

Fairness Without Harm: An Influence-Guided Active Sampling Approach
par: Pang, Jinlong, et autres
Publié: (2024)

No Action Without a NOD: A Heterogeneous Multi-Agent Architecture for Reliable Service Agents
par: Yang, Zixu, et autres
Publié: (2026)

Stop Automating Peer Review Without Rigorous Evaluation
par: Baumann, Joachim, et autres
Publié: (2026)

Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
par: Zhang, Yuxiang, et autres
Publié: (2025)

Boost Self-Supervised Dataset Distillation via Parameterization, Predefined Augmentation, and Approximation
par: Yu, Sheng-Feng, et autres
Publié: (2025)

Action Space Reduction Strategies for Reinforcement Learning in Autonomous Driving
par: Delavari, Elahe, et autres
Publié: (2025)

Autonomous Evaluation and Refinement of Digital Agents
par: Pan, Jiayi, et autres
Publié: (2024)

Perception Without Vision for Trajectory Prediction: Ego Vehicle Dynamics as Scene Representation for Efficient Active Learning in Autonomous Driving
par: Greer, Ross, et autres
Publié: (2024)

Towards Human-Like Driving: Active Inference in Autonomous Vehicle Control
par: Delavari, Elahe, et autres
Publié: (2024)

ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning
par: Melikidze, Davit, et autres
Publié: (2026)

Uncertainty-Aware Measurement of Scenario Suite Representativeness for Autonomous Systems
par: Chakherlou, Robab Aghazadeh, et autres
Publié: (2025)

Learning CLI Agents with Structured Action Credit under Selective Observation
par: Su, Haoyang, et autres
Publié: (2026)

Human-Inspired Continuous Learning of Internal Reasoning Processes: Learning How to Think for Adaptive AI Systems
par: Su, Hong
Publié: (2026)

Human Simulation Computation: A Human-Inspired Framework for Adaptive AI Systems
par: Su, Hong
Publié: (2026)

Obtaining Optimal Spiking Neural Network in Sequence Learning via CRNN-SNN Conversion
par: Su, Jiahao, et autres
Publié: (2024)

Language Models Can Learn from Verbal Feedback Without Scalar Rewards
par: Luo, Renjie, et autres
Publié: (2025)

Online Feedback Efficient Active Target Discovery in Partially Observable Environments
par: Sarkar, Anindya, et autres
Publié: (2025)

Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard
par: Abdelnabi, Sahar, et autres
Publié: (2026)

Autonomous Action Runtime Management(AARM):A System Specification for Securing AI-Driven Actions at Runtime
par: Errico, Herman
Publié: (2026)

Feedback Forensics: A Toolkit to Measure AI Personality
par: Findeis, Arduin, et autres
Publié: (2025)

Beyond Predefined Schemas: TRACE-KG for Context-Enriched Knowledge Graphs from Complex Documents
par: Abolhasani, Mohammad Sadeq, et autres
Publié: (2026)

Evaluate-as-Action: Self-Evaluated Process Rewards for Retrieval-Augmented Agents
par: Shu, Jiangming, et autres
Publié: (2026)

MCP-Zero: Active Tool Discovery for Autonomous LLM Agents
par: Fei, Xiang, et autres
Publié: (2025)

Emergency Preemption Without Online Exploration: A Decision Transformer Approach
par: Su, Haoran, et autres
Publié: (2026)

A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation
par: Cao, Cong, et autres
Publié: (2026)

QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents
par: Nader, Jordan Abi, et autres
Publié: (2025)

Detecting Systematic Weaknesses in Vision Models along Predefined Human-Understandable Dimensions
par: Gannamaneni, Sujan Sai, et autres
Publié: (2025)

A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback
par: Tabassum, Anika, et autres
Publié: (2026)

Understanding Mental States in Active and Autonomous Driving with EEG
par: Angkan, Prithila, et autres
Publié: (2025)

GroundAct: Can LLM Agents Ground Actions in Environmental States?
par: Wang, Zixuan, et autres
Publié: (2025)

Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
par: Ye, Bowen, et autres
Publié: (2026)

MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs
par: Hsu, Hsin-Ling, et autres
Publié: (2026)