arXiv cs.CL· Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Tianshu Fu, Daren Zha·· 12 小时前AI 评分20
ROUTEAUDIT：面向预算受限多验证器路由的交互感知识别方法
ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier Routing
AI 导读
ROUTEAUDIT 将验证器路由形式化为契约条件下的识别问题，通过契约格、策略无关响应带和请求级界，在自适应策略下分离路由归因。在 1,319 条留出任务请求上，学习策略与 RLVR 研究分别报告质量 0.9522 和 0.9553，匹配静态基线为 0.9484，RLVR 与静态的配对差异为 +0.0068，请求配对区间 [0.0015,0.0122]。
正文 · 原文
Abstract:Adaptive multi-verifier systems are commonly compared through endpoint quality-cost gaps, even when the verifier catalog, availability, accounting, information filtration, or scorer changes with the policy. We formulate verifier routing as a contract-conditioned identification problem. The contract records request support, verifier catalog, realized availability, resource accounting, online filtration, and post-trace scoring; a matched route contrast changes only the policy coordinate. ROUTEAUDIT adds three measurable objects to this contract. A contract lattice averages coordinate increments over every admissible bridge order and reports the resulting attribution together with its path sensitivity. A policy-independent response tape identifies paired sequential contrasts when adaptive policies reveal different observations. For incomplete matching, request-level bounds use whichever potential outcome remains observed and give a sharp finite-population interval. The protocol commits paid observations and ledger events before the oracle join and returns an attribution certificate for each comparison. On two held-out raw-tail caches, matched static SF+SA equals the cascade, assigning the apparent gains of 0.1797 and 0.1250 over full static to the verifier-set edge. On 1,319 held-out task requests, the learned and RLVR studies report quality 0.9522 and 0.9553 versus 0.9484 for matched static; the RLVR-static paired difference is +0.0068 with a request-paired interval $[0.0015,0.0122]$ and a training-seed-by-request hierarchical interval $[0.0006,0.0131]$. Controlled attribution recovery yields route mean absolute error 0.0011 and endpoint reconstruction error 0.0004. Factorial, bridge-order, and stochastic-provider studies evaluate the certificate interface; RLVR supplies a learned-policy stress test under the same identification contract.
| Comments: | 45 pages, 15 figures |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.02808 [cs.AI] |
| (or arXiv:2610.02808v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02808 arXiv-issued DOI via DataCite |
Submission history
From: Miaobo Hu [view email]
[v1]
Fri, 2 Oct 2026 04:59:24 UTC (1,533 KB)
[v2]
Fri, 16 Oct 2026 12:24:21 UTC (1,532 KB)
来源：arXiv cs.CL · arxiv.org