Source author record

Wenqing Wang

Wenqing Wang appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Computation and Language Artificial Intelligence math.AP math.FA

Catalog footprint

What is connected

3works

4topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States

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.

preprint2025arXiv

SagaScale: A Realistic, Scalable, and High-Quality Long-Context Benchmark Built from Full-Length Novels

Large Language Models (LLMs) have shown significant progress, but understanding long and complex documents remains challenging. Many long-context benchmarks have been proposed, but they face several limitations, including task realism, data scalability, and data quality. To this end, we introduce SagaScale, a realistic, scalable, and high-quality long-context benchmark built from full-length novels. The entire benchmark is constructed using an automated data collection pipeline that utilizes external resources (e.g., Wikipedia pages) to curate question-answer pairs. Critically, these external resources are provided only for benchmark construction and not during evaluation, which allows LLMs to curate complex questions that go beyond what they can answer during evaluation. SagaScale is also bilingual and offers the largest context length to date, with average token counts exceeding 250K for English novels and 320K for Chinese novels. Our evaluation across 12 frontier LLMs and three long-context methods -- Naïve RAG, Agentic RAG, and Long Context -- yields key insights, including: (1) Directly supplying the full context to the LLM can outperform other methods by a large margin; (2) Most LLMs still struggle with lengthy contexts, but Gemini-2.5-Pro stands out as an exception; and (3) Agentic RAG effectively addresses the retrieval bottleneck in Naïve RAG. Finally, we publicly release the SagaScale benchmark and our data collection codebase to facilitate future research.

preprint2022arXiv

A constrained minimization problem related to two coupled pseudo-relativistic Hartree equations

We are concerned with the following constrained minimization problem: $$e(a_{1},a_{2},β) := \inf\left\{E_{a_{1},a_{2},β}(u_{1},u_{2}): \|u_{1}\|_{L^{2}(\mathbb{R}^{3})} = \|u_{2}\|_{L^{2}(\mathbb{R}^{3})} = 1\right\},$$ where $E_{a_{1},a_{2},β}$ is the energy functional associated to two coupled pseudo-relativistic Hartree equations involving three parameters $a_{1}, a_{2}, β$ and two trapping potentials $V_1(x)$ and $V_2(x)$. In this paper, we obtain the existence of minimizers of $e(a_{1},a_{2},β)$ for possible $a_{1}, a_{2}$ and $β$ under suitable conditions on the potentials, which generalizes the results of the papers [16,17,18] in different senses.