A fundamental gap between generation fluency and reasoning ability is uncovered, a pronounced ''inverse scaling effect'' where larger models can underperform in domain-specific reasoning, and systemic bottlenecks across all SOTA models are identified, exposing fundamental limitations of current architectures.
Guangtao Nie, Huimu Wang, Gewei Lu et al.· Proceedings of the 32nd ACM...· 0 citations
CoSkill is a unified multi-agent RL framework that recasts the static meta-skill workflow as a learnable Meta-Skill Agent and jointly trains it with a Reasoning Agent over a hierarchical skill library and achieves superior early-stage sample efficiency, asymptotic performance, and wall-clock efficiency.
Jin-Yuan Feng, Dong-Min Li, Yi-Qun Chen et al.· 0 citations
A fundamental gap between generation fluency and reasoning ability is uncovered, a pronounced ''inverse scaling effect'' where larger models can underperform in domain-specific reasoning, and systemic bottlenecks across all SOTA models are identified, exposing fundamental limitations of current architectures.
Guangtao Nie, Huimu Wang, Gewei Lu et al.· Proceedings of the 32nd ACM...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
