SpecAgent:工具使用智能體的軌跡級推測與語義驗證
Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents
SpecAgent 讓小模型草擬智能體的工具使用步驟,再由大模型以單次並行預填充驗證,以降低延遲和記憶體用量,同時保留大部分任務品質。τ^2-Bench 上,成功率與大模型相差不足 1 個百分點,記憶體流量和耗時約減半;在 AutomationBench、VitaBench 則回補 44-75% 的品質差距。
Published on Oct 15
Authors:
,
,
,
Abstract
SpecAgent improves agent efficiency by having a small model draft tool-use steps that a large model verifies in parallel, reducing latency and memory use while preserving quality.
Large language model agents solve tasks through long sequences of tool calls, and the prevailing design has a single strong model generate every step, although many steps are routine enough for a much smaller model. Existing ways of sharing this work keep the strong model as the generator: routers and collaborative agents decide which model handles each query or step, and speculative methods check a small model's drafts one step at a time, usually against the strong model's own action. We introduce SpecAgent, a collaboration protocol that turns the strong model from the author of each step into a reviewer of steps drafted by a weak model. The weak model executes read-only tool calls as it drafts, so that every step is grounded in real observations, and holds the first action that would modify the environment. The strong model then verifies the drafted segment in a single prefill pass, commits the longest prefix it judges semantically valid, and repairs the first rejected step. Because verification replaces autoregressive decoding with parallel prefill, the strong model decodes only short verdicts and occasional repairs rather than every step. On τ^2-Bench, SpecAgent comes within one point of the strong model's success rate while roughly halving memory traffic and wall time, and on AutomationBench and VitaBench it recovers 44-75% of the quality gap while lowering both. In an edge-cloud deployment on MCP-Atlas with three cloud models, it closes 53-75% of the weak-strong quality gap while the strong model generates at most half as many tokens. These results suggest that a strong model need not author every step of an agent: reviewing grounded drafts retains most of its quality while cutting both latency and memory traffic.
View arXiv page View PDF Project page GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.21463
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.21463 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.21463 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.21463 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co