How I Study AI - Learn AI Papers & Lectures the Easy Way

Tool Verification for Test-Time Reinforcement Learning

Intermediate

Ruotong Liao, Nikolai Röhrich et al.Mar 2arXiv

The paper fixes a big flaw in test-time reinforcement learning (TTRL): when many wrong answers agree, the model rewards the mistake and gets stuck.

#test-time reinforcement learning#verification-weighted voting#tool verification

SCOPE: Prompt Evolution for Enhancing Agent Effectiveness

Beginner

Zehua Pei, Hui-Ling Zhen et al.Dec 17arXiv

SCOPE lets AI agents rewrite their own instructions while they are working, so they can fix mistakes and get smarter on the next step, not just the next task.

#prompt evolution#LLM agents#context management

EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models

Intermediate

Zechen Bai, Chen Gao et al.Dec 16arXiv

Robots usually learn by copying many demonstrations, which is expensive and makes them brittle when things change.

#EVOLVE-VLA#test-time training#vision-language-action

Papers3

Tool Verification for Test-Time Reinforcement Learning

SCOPE: Prompt Evolution for Enhancing Agent Effectiveness

EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models