Search papers, labs, and topics across Lattice.
The paper introduces SCOUT, a novel paradigm for Long-Text Understanding (LTU) that actively forages for relevant information within a document instead of passively processing the entire context. SCOUT uses state-level gap diagnosis to guide coarse-to-fine exploration and anchored state updates, progressively refining its epistemic state. Experiments demonstrate that SCOUT achieves state-of-the-art performance while reducing token consumption by up to 8x and maintaining stability as context length increases.
Achieve 8x token reduction in million-token document understanding without sacrificing accuracy by having the LLM actively search for relevant information like a foraging animal.
Long-Text Understanding (LTU) at million-token scale requires balancing reasoning fidelity with computational efficiency. Frontier long-context LLMs can process millions of token contexts end-to-end, but they suffer from high token consumption and attention dilution. In parallel, specialized LTU agents often sacrifice fidelity through task-agnostic abstractions like graph construction or indexing. We identify a key insight for LTU: query-relevant information is typically sparse relative to the full document, so effective reasoning should rely on a query-sufficient subset rather than the entire context. To address this, we propose SCOUT, a new paradigm for LTU that shifts from passive processing to active information foraging. It treats the document as an explorable environment and answers from a compact, provenance-grounded epistemic state. Guided by state-level gap diagnosis, SCOUT adaptively alternates between coarse-to-fine exploration and anchored state updates that progressively contract its epistemic state toward query sufficiency. Experiments show that SCOUT matches state-of-the-art proprietary models while reducing token consumption by up to 8x. Moreover, SCOUT remains stable as context length scales, substantially alleviating the practical cost-performance trade-off.