Skip to content
All tags

#acl2026

2 posts
aideep-diveDeep Research 前沿

Test-Time Scaling: BrowseConf and Confidence-Guided Reasoning

The previous articles covered evaluation. This one covers another dimension: how to dynamically allocate compute during reasoning. BrowseConf's core insight is that an agent's self-declared 'confidence' can predict answer accuracy. High confidence uses fewer resources; low confidence searches more rounds.

#deep-research#test-time-scaling#browseconf#confidence#acl2026
aideep-diveDeep Research 前沿

WebWeaver & DeepPlanner: Dual-Agent Architecture and Planning Optimization

Previous articles covered training from scratch and long-horizon memory. This one goes deeper: how to make the agent's 'planning' itself better? WebWeaver tackles it architecturally (dual-agent iterative outline optimization). DeepPlanner tackles it through training (advantage shaping for planning tokens). Both point to the same conclusion: planning is the ceiling of deep research.

#deep-research#planning#dual-agent#advantage-shaping#webweaver#deepplanner#iclr2026#acl2026