Deep-research agents conduct long-horizon investigations through iterative search, evidence evaluation, belief revision, and synthesis.
However, they may commit to claims before sufficient evidence is available, causing later reasoning to reinforce an incorrect interpretation.
We introduce DeepRewind
DeepRewind, an additive control layer for reversible deep research that represents the agent's evolving epistemic state as a typed graph of sources, evidence, claims, hypotheses, assumptions, commitments, plans, and drafts.
Before accepting an intermediate conclusion, a prompt-based world model predicts its impact and estimates reversibility based on hypothesis narrowing, information loss, recovery cost, and contradiction-trigger coverage.
Binary Controller and Consistency Monitor
A binary controller blocks risky commitments, while a consistency monitor performs dependency-aware rollback when later evidence invalidates them.
Performance on DRBench and LiveDRBench
Across DRBench and LiveDRBench, DeepRewind improves insight recall by 3.6 percentage points and reduces premature commitments by 59.1% relative to Open Deep Research.