SLEUTH: Epistemic Working Memory Scales Multi-Hop Reasoning in Language Agents

Jul 15, 2026

Researchers present SLEUTH, a structured epistemic working memory system that enables language agents to explicitly track confirmed facts, active hypotheses, and open questions during multi-hop reasoning tasks. Evaluated on five multi-hop benchmarks, SLEUTH improves accuracy by up to 11 points on 4-hop chains and outperforms Reflexion without requiring multiple episodes. The study demonstrates that maintaining an organized epistemic state is crucial for scaling multi-hop reasoning, independent of raw model capability.

Why it matters: This work addresses the core challenge of context dilution in language agents and shows that structured reasoning organization, rather than model size alone, is key to reliable multi-step tool use.

Full story at: arXiv Machine Learning ↗