Track, Rank, Crack: Epistemic Working Memory Scales Multi-Hop Reasoning in Language Agents

The SLEUTH framework improves multi-hop reasoning in language agents by explicitly managing epistemic working memory to prevent context dilution during long reasoning chains.

Firefly links to the original publisher. The summary above is AI-generated for orientation and may differ from the source. The “current rank score” decays over time so newer significant stories surface first.