Outcome-based reinforcement learning provides coarse supervision for long-horizon LLM agents: failed trajectories may contain correct steps, while successful trajectories can contain errors. Trajectory-level skills can also shift teacher preferences at unrelated steps, introducing off-target distillation signals. We in...
The findings support on-policy distillation as an effective warmup for agentic RLVR and identify initial reward discovery as a mechanism that can contribute to the observed acceleration.
Yi-Tong Qiao, Tian-Tian He, Lei Liu et al.· arXiv.org· 0 citations
In hospital workflows, electronic health records (EHRs) are often noisy, and may not contain the evidence needed to confirm events or measurements referenced in a clinical query. Even when database retrieval succeeds, clinical agents can overlook such discrepancies and return plausible but unsupported answers. We intro...
Yi-Tong Qiao, Yan-Cheng Jin, Lei Liu et al.· arXiv.org· 0 citations
It is demonstrated that verifying evidential support before submission can make diagnostic decisions more reliable, and decouples diagnosis generation from submission through an offline Contrastive Diagnostic Wiki and three online control stages, namely observation management, proposal and witness verification, and dia...
Ke-Hua Feng, Yun-Sheng Lu, Yi-Tong Qiao et al.· 0 citations
Efficient On-Policy Self-Distilled Safety Alignment (EOPSA), which concentrates computational and gradient budgets exclusively on reliably supervised, safety-critical tokens, is proposed, consistently outperforming full-token distillation baselines in both safety compliance and reasoning retention.
Qi-Rui Liu, Yi-Chen Sun, Yan Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.