跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-12AI 評分34

Dream2Discern:從困難潛在變體中學習,預測多智能體系統的執行時失敗

Dream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems

AI 導讀

Dream2Discern 透過自我引導生成困難潛在變體,訓練多智能體系統的執行時審計器預測執行結果,無需額外收集軌跡或驗證結果即可提升準確度。它在 AFTraj-2K 和 StepShield 兩項基準測試均取得超過 90% 的軌跡層級加權準確率,並兼顧預測準確度與及時性。

正文

Published on Oct 12

Authors:

,

,

Abstract

Dream2Discern improves runtime auditing of multi-agent systems by implicitly augmenting training data through self-guided hard example generation, boosting accuracy without new trajectory verification.

Reliable deployment of LLM-based multi-agent systems calls for runtime auditors that predict terminal outcomes from observed execution prefixes. These auditors typically learn from a limited corpus of trajectories with verified outcomes. Expanding this corpus requires costly execution and verification, yet broader failure coverage alone provides no explicit criterion for identifying prefixes that the current auditor finds difficult to classify. To this end, we propose Dream2Discern, a runtime auditor trained through implicit augmentation guided by its own prediction loss. During Dream, we select perturbations of the auditor's representation operators to increase prediction loss on recorded prefixes, yielding hard latent variants. During Discern, the auditor learns to predict execution outcomes from these variants using the original labels. The variants are regenerated as the auditor learns, turning a limited corpus into a renewable source of hard examples and requiring no additional trajectory collection or outcome verification. Extensive evaluations on AFTraj-2K and StepShield show that Dream2Discern outperforms competitive failure auditors and achieves over 90% trajectory-level weighted accuracy on both benchmarks while balancing prediction accuracy and timeliness. Project page: https://zbox1005.github.io/dream2discern-project/

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.16071

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/2610.16071 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/2610.16071 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/2610.16071 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