This work builds a trajectory-level diagnostic pipeline that evaluates both answer correctness and evidence-grounding quality under a unified ReAct-style scaffold and introduces a six-category taxonomy covering modality shortcuts, phantom grounding, wrong-evidence-right-answer cases, over-retrieval laundering, cross-mo...
Zheng-Xian Wu, Junjie Gao, Kai Yang· arXiv.org· 0 citations
TreeGraft is a multi-drafter framework in which drafters of different costs jointly construct a shared draft tree that outperforms the better of the two fixed single-drafter endpoint strategies by 15.1% on average and reaches a maximum gain of 26.6%.
Jiaming Fan, D. Cao, Can-Chen Huang et al.· 0 citations
This work introduces SearchOS, a system-level multi-agent framework that turns fragile, implicit search progress into explicit, persistent, and shared state, and introduces a Search Tool Middleware Harness that intercepts model and tool interactions to record grounded evidence and react to stalls or budget exhaustion.