Meiru Zhang
Publications
A Benchmark for Deep Information Synthesis
Large language model (LLM)-based agents are increasingly used to solve complex tasks involving tool use, such as web browsing, code execution, and data analysis. However, current evaluation benchmarks do not adequately assess their ability to solve real-world tasks that require synthesizing information from multiple sources and inferring insights beyond simple fact retrieval. To address this, we introduce DEEPSYNTH, a novel benchmark designed to evaluate agents on realistic, time-consuming problems that combine information gathering, synthesis, and structured reasoning to produce insights. DEEPSYNTH contains 120 tasks collected across 7 domains and data sources covering 67 countries. DEEPSYNTH is constructed using a multi-stage data collection pipeline that requires annotators to collect official data sources, create hypotheses, perform manual analysis, and design tasks with verifiable answers. When evaluated on DEEPSYNTH, 11 state-of-the-art LLMs and deep research agents achieve a maximum F1 score of 8.97 and 17.5 on the LLM-judge metric, underscoring the difficulty of the benchmark. Our analysis reveals that current agents struggle with hallucinations and reasoning over large information spaces, highlighting DEEPSYNTH as a crucial benchmark for guiding future research.
Failure Modes in Multi-Hop QA: The Weakest Link Law and the Recognition Bottleneck
Despite scaling to massive context windows, Large Language Models (LLMs) struggle with multi-hop reasoning due to inherent position bias, which causes them to overlook information at certain positions. Whether these failures stem from an inability to locate evidence (recognition failure) or integrate it (synthesis failure) is unclear. We introduce Multi-Focus Attention Instruction (MFAI), a semantic probe to disentangle these mechanisms by explicitly steering attention towards selected positions. Across 5 LLMs on two multi-hop QA tasks (MuSiQue and NeoQA), we establish the "Weakest Link Law": multi-hop reasoning performance collapses to the performance level of the least visible evidence. Crucially, this failure is governed by absolute position rather than the linear distance between facts (performance variance $<3%$). We further identify a duality in attention steering: while matched MFAI resolves recognition bottlenecks, improving accuracy by up to 11.5% in low-visibility positions, misleading MFAI triggers confusion in real-world tasks but is successfully filtered in synthetic tasks. Finally, we demonstrate that "thinking" models that utilize System-2 reasoning, effectively locate and integrate the required information, matching gold-only baselines even in noisy, long-context settings.