A robust framework that integrates RLAIF (Reinforcement Learning from AI Feedback) and a novel Multi-Agent Consensus Protocol (MACP) is proposed, demonstrating a 14.5% improvement in F1-score across highly complex multimodal domains compared to classical baselines.
This work introduces Co-RL, a framework in which multiple decoupled models, sharing no parameters, are simultaneously optimized through RL using rewards derived from their peers, and shows that unsupervised reasoning can emerge through cooperative multi-agent training.
Yunhao Yang, Yuexin Bian, Yun-Jie Tian et al.· 1 citation
Evaluations across scientific, multimodal, agentic, and general-purpose benchmarks show that Intern-S2-Preview-397B achieves competitive or leading results in multiple settings.
Lei Bai, Jiaqi Cao, Chiyu Chen et al.· 3 citations
LLM-guided program evolution has enabled discoveries in mathematics and computational optimization, raising the prospect of reinforcement learning (RL) algorithms that self-evolve to improve how agents learn. However, realizing this prospect faces two obstacles. Joint search over coupled algorithmic components is diffi...
Hao-Ran Li, Z. Ge, Xiao-Ming Yuan et al.· 0 citations
Overall, a systematic understanding of how RL reshapes VLA policies is provided by studying how learned signals are encoded in parameter space, offering insights into more efficient and interpretable VLA post-training.
Minjae Oh, Yoonah Park, Jongwon Lim et al.· 0 citations
Results indicate that with zero curated data, OPT-Zero matches state-of-the-art data-dependent methods while exhibiting substantially stronger generalizability, establishing self-play training as a highly scalable paradigm for advancing LLM reasoning in modeling and solving optimization problems.
Xia Jiang, Yao-Xin Wu, Chen-Yu Zhou et al.· 0 citations
Self-evolving LLM agents promise to improve autonomously through continual interaction and learning, reducing their dependence on manually curated supervision. Realizing this promise requires not only updating the agent, but also evolving its training experience as its capabilities change. However, most existing pipeli...
Wei Yang, Shawn Li, Yuehan Qin et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
