#capability-expansion News & Analysis

2 articles tagged with #capability-expansion. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AIBullisharXiv – CS AI · Apr 157/10

🧠

Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models

Researchers introduce Ariadne, a framework demonstrating that Reinforcement Learning with Verifiable Rewards (RLVR) expands spatial reasoning capabilities in Vision-Language Models beyond their base distribution. Testing on synthetic mazes and real-world navigation benchmarks shows the technique enables models to solve previously unsolvable problems, suggesting genuine capability expansion rather than sampling efficiency.

AINeutralarXiv – CS AI · May 126/10

🧠

AIPO: : Learning to Reason from Active Interaction

Researchers introduce AIPO, a reinforcement learning framework that enhances large language model reasoning by enabling active consultation with collaborative agents during training. The method addresses exploration limitations in current RL approaches and demonstrates consistent performance improvements across multiple mathematical and coding benchmarks.