CorVer (Corpus Verify) is a lightweight training-time approach to process supervision that derives sentence-level rewards from corpus co-occurrence statistics and outperforms the unmodified models in all standard factual-QA settings.
Shi-Chen Fan, Hao-Chang Hao, De-Hai Min et al.· 5 citations
This work introduces Agentic Commerce World (ACWorld), an environment for evaluating such agents across ongoing transactions, and validates agent actions before updating shared transaction state and records the resulting interactions, making agent behavior auditable and evaluation reproducible.
Shi-Chen Fan, Ming-Dai Yang, Duo Wang et al.· 2 citations· ⚡1
It is shown that this felt penalty becomes behaviorally binding through SPARC, a byte-clean code-gated reflection mechanism: LLM merchants fabricate when lying is free but restrain themselves when fabrication costs them sales, a self-interested response rather than compliance.