Dr Drift-Bench++ is introduced, a principled benchmark construction pipeline for verified executable tasks with controlled misalignment and intent shifts, along with an interaction protocol featuring finite patience, diverse simulated users, and silent interaction-conditioned shifts, which offers a foundation for evalu...
Zhe-Yuan Zhang, M. Chao, Ke Xiao et al.· arXiv.org· 4 citations
Quantitative and qualitative evaluations on multi-shot story generation demonstrate that the Complementary Retrieval-Augmented Prompting method consistently outperforms recent-frame, memory-based, and entity-level retrieval baselines in cross-shot consistency and text-controllability.
Xiang-Han Wei, Xiao-Da Yang, Zhi Wang et al.· arXiv.org· 0 citations
An agent can complete a task while exhibiting undesirable behavior during execution. Developers need tests for the specific behaviors encountered in deployment, beyond fixed benchmark suites. We present TraceDance, an agent system that constructs targeted benchmarks from deployment traces for user-specified undesirable...
De-Hai Min, Dao-An Zhang, Yiming Zeng et al.· 1 citation
R-OPD, a gradient-triggered curriculum that adaptively selects when to revisit initial-student trajectories, improves average accuracy over continued current-policy sampling and produces longer responses, suggesting that well-timed revisits help students use more of their reasoning capacity.
Ling Hu, Tian-Le Xia, Yi-Ding Sun et al.· 0 citations
RouteOPD (Routed On-Policy Distillation), which decomposes local teacher--student disagreement into student-excess sources and teacher-deficit destinations and couples them into explicit transport pairs and demonstrates the effectiveness of explicitly modeling probability transport in on-policy distillation.
Tian-Le Xia, Ling Hu, Yi-Ding Sun 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.