method · first seen 11 Oct 2026
reinforcement learning from rubric-based rewards
Training with rewards computed by scoring intermediate reasoning steps against a set of criteria.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought ReasoningPapers · 11 Oct 2026 · Fan Yang, Lifeng Chen, Yipu Wang, Han Wang, Feilong Chen, Yidong Ma, Zhiyang Che…
- Reward Engine: Reward-Centric Self-Evolution for Open-Ended Tool AgentsPapers · 16 Oct 2026 · Litong Feng, Ji Qi, Yiran Cheng, Shaowu Pan, Xinyu Zhang, Qijun Li
Latest sources
- Reward Engine: Reward-Centric Self-Evolution for Open-Ended Tool AgentsPapers · 16 Oct 2026 · Litong Feng, Ji Qi, Yiran Cheng, Shaowu Pan, Xinyu Zhang, Qijun Li
- Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought ReasoningPapers · 11 Oct 2026 · Fan Yang, Lifeng Chen, Yipu Wang, Han Wang, Feilong Chen, Yidong Ma, Zhiyang Che…