activity
20242026
collaborators
Showing cs.AIShow all

7 papers · 1 filter

cs.AI2026

SGR-Bench: Benchmarking Search Agents on State-Gated Retrieval

Ningyuan Li, Haiyang Shen, Mugeng Liu +4

Recent advances in large language models and tool-using agents have expanded the range of benchmarked web tasks. Yet an important class of specialized retrieval tasks remains under…

cs.AI2026

Teaching AI Through Benchmark Construction: QuestBench as a Course-Based Practice for Accountable Knowledge Work

Haiyang Shen, Jiuzheng Wang, Taian Guo +9

As AI becomes part of everyday learning, many courses teach students to use it mainly as a productivity tool: how to prompt, search, summarize, write, code, and use tools more effi…

cs.AI2026

MindLoom: Composing Thought Modes for Frontier-Level Reasoning Data Synthesis

Haiyang Shen, Taian Guo, Xuanzhong Chen +11

Although LLMs have made substantial progress in reasoning, systematically producing frontier-level reasoning data remains difficult. Existing synthesis methods often have limited v…

cs.AI2026

DeepWeb-Bench: A Deep Research Benchmark Demanding Massive Cross-Source Evidence and Long-Horizon Derivation

Sixiong Xie, Zhuofan Shi, Haiyang Shen +8

Deep research, in which an agent searches the open web, collects evidence, and derives an answer through extended reasoning, is a prominent use case for frontier language models. F…

cs.AI2026

Rethinking Explainable Disease Prediction: Synergizing Accuracy and Reliability via Reflective Cognitive Architecture

Zijian Shao, Haiyang Shen, Mugeng Liu +4

In clinical decision-making, predictive models face a persistent trade-off: accurate models are often opaque "black boxes," while interpretable methods frequently lack predictive p…

cs.AI2026

DRAGON: Domain-specific Robust Automatic Data Generation for RAG Optimization

Haiyang Shen, Hang Yan, Zhongshi Xing +6

Retrieval-augmented generation (RAG) can substantially enhance the performance of LLMs on knowledge-intensive tasks. Various RAG paradigms - including vanilla, planning-based, and…