arXiv:cs.AI· Ali Afoud, Jie JW Wu·· 6 小时前
将验证作为 LLM Agent 的架构层:V-Model 设计及确定性核心的试点研究
Verification as an Architectural Layer for LLM Agents: A V-Model Design, and a Pilot Study of Its Deterministic Core
AI 导读
研究提出把验证作为 LLM Agent 的独立架构层,借鉴软件工程的 V-Model 让每个规格层级配对专属验证器,由确定性控制器执行裁决,仅验证结果写入记忆。
正文
Abstract:Large language model (LLM) agents built on the ReAct pattern concentrate four responsibilities in one model: selecting a strategy, choosing each action, formatting it, and judging whether the result is adequate. Nothing outside the generative loop can reject its output, so an agent that cannot make progress does not report failure; it runs until an external budget stops it. We propose treating verification as an architectural layer by adapting the V-model from software engineering: specification levels descend from requirements to individual steps, each level is paired with a dedicated verifier, a deterministic controller enforces every verdict, and only verification outcomes write to memory, so a rejection localizes the level that introduced the fault and an agent halts by declining rather than by exhaustion. Each verifier separates a zero-cost deterministic \emph{gate} from an optional LLM \emph{judge}, so the contribution and cost of each can be measured independently. We report a pilot implementing the acceptance- and unit-level verifier pairs, comparing five configurations that share one executor, tool set, and scorer and differ only in verification, on the four-hop stratum of MuSiQue with an 8B-parameter backbone. Across 47 executions, the two unverified configurations answered none of ten questions, every run ending at a step cap or provider token limit; the verified configuration without a planner answered eight and abstained on the rest. Deterministic gates produced eight of the nine observed corrections at zero marginal cost, and planning degraded performance once verification was present. These results characterize termination behavior, not accuracy at scale; we outline a twelve-month plan to complete and evaluate the full architecture, including the integration-level pair the pilot omits.
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.31937 [cs.SE] |
| (or arXiv:2609.31937v2 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2609.31937 arXiv-issued DOI via DataCite |
Submission history
From: Ali Afoud [view email]
[v1]
Fri, 25 Sep 2026 19:30:58 UTC (26 KB)
[v2]
Sat, 10 Oct 2026 04:25:59 UTC (26 KB)
来源:arXiv:cs.AI · arxiv.org