Efficient Test-Time Adaptation through Human-AI Interaction
cs.AI
Submitted: 2026-09-03
Updated: 2026-09-03
Code: https://github.com/zorazrw/tahi-agent-adaptation
Terminology
Sources
- How LLMs Distort Our Written Language
- Gym-Anything: Turn any Software into an Agent Environment
- Aligning Language Models from User Interactions
- Evaluating Large Language Models Trained on Code
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
- What do you mean by human-AI collaboration: Prerequisite functions and the affordances needed to achieve it
- Continual Learning via Sparse Memory Finetuning
- BAGEL: Bootstrapping Agents by Guiding Exploration with Language
- MemGPT: Towards LLMs as Operating Systems
- CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks
- Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction
- Understanding the performance gap between online and offline alignment algorithms
- Learning, Fast and Slow: Towards LLMs That Adapt Continually
- APEX-Agents
- OpenCUA: Open Foundations for Computer-Use Agents
- OpenClaw-RL: Train Any Agent Simply by Talking
- How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations
- Toward an Evaluation Science for Generative AI Systems
- SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning
- TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection