No AI summary available for this article.
Why It Matters
Reinforcement learning (RL) across multiple domains can broaden the reasoning capabilities of large language models (LLMs), yet joint training often degrades individual-domain performance and can destabilize optimization.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Reinforcement learning (RL) across multiple domains can broaden the reasoning capabilities of large language models (LLMs), yet joint training often degrades individual-domain performance and can destabilize optimization. Existing work typically diagnoses such interference from a single-step view using first-order gradient alignment or curvature-based proxies. We show that this view can miss a critical form of sequential interference: same-point domain gradients may remain nearly orthogonal even when consecutive realized updates partially reverse one another in output space. We further show th...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.06469v1 · Indexed about 10 hours ago