STORM manages agent states in shared workspaces to ensure consistent views and resolve conflicting edits at write time, outperforming git-worktree baselines by +18.7 on Commit0-Lite and +1.4 on PaperBench while reaching combined scores of 87.6 and 78.2.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Active information seeking via search tools, when combined with multi-candidate context pruning during training, produces consistent gains on translation, health, and reasoning tasks over naive tool addition or no-tool baselines.
citing papers explorer
-
Multi-agent Collaboration with State Management
STORM manages agent states in shared workspaces to ensure consistent views and resolve conflicting edits at write time, outperforming git-worktree baselines by +18.7 on Commit0-Lite and +1.4 on PaperBench while reaching combined scores of 87.6 and 78.2.
-
Context Training with Active Information Seeking
Active information seeking via search tools, when combined with multi-candidate context pruning during training, produces consistent gains on translation, health, and reasoning tasks over naive tool addition or no-tool baselines.