Multi-agent LLM systems often fail not for lack of candidate answers, but because they have no persistent mechanism for deciding which incompatible claim should currently be trusted. Majority vote, debate, and judge-based selection choose an output without recording which claim wins, which is contested, or why a later...
Heng Zhou, Lian Zhang, Yutao Fan et al.· 0 citations
Recursive self-improvement (RSI) lets a system improve the model-building machinery from its own failures, so every later model inherits the gain. Yet RSI has been validated almost exclusively on coding and formal benchmarks such as science QA and mathematics. This format bound limits RSI to improvement within a machin...
Zi-Hang Tan, Lei-Xin Sun, Zi-Tong Shi et al.· 0 citations
Experiments across diverse models, benchmarks, and agent harnesses show that supervised fine-tuning on SKT-generated trajectories consistently improves skill-use performance, establishing verified data synthesis as an effective and scalable approach for skill-use training.
Zelin Tan, Yi-Qun Zhang, Hao Li et al.· 2 citations
We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward designs. Outcome reward models (ORM) evaluate only final-answer correctness, trea...
Zelin Tan, Zhouliang Yu, Bo-Cheng Lin et al.· arXiv.org· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
