Sung Ju Hwang

LLM agents can now reliably track and fulfill complex deliverable requirements across numerous files without losing context, thanks to an environment-side "tab" that acts as a persistent, shared task ledger.

LLM agents waste immense token budgets repeatedly rediscovering identical cross-document links on every query—pre-indexing corpora into an offline entity-document graph solves fragmented multi-hop retrieval while actually lowering token costs.

Extra test-time "thinking" cannot recover missing parametric facts, but teaching small reasoning models to recognize their own knowledge boundaries and selectively query larger models lets a 4B model outperform a 14B baseline at nearly a third of the serving cost.