Skip to content

Author

Mengru Wang

We have 7 of 31 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Aug 2026

Towards principled knowledge editing methods for large language model reasoning

It is argued that effective knowledge editing must account for the intricate nature of knowledge representation, and three promising research directions are proposed that respect the complexity of knowledge representation in a real-world setting.

Ningyu Zhang, Yunzhi Yao, Jiaxin Qin et al. · 0 citations
#artificial intelligence Preprint May 2026

SciAtlas: A Computable Atlas of Science for Knowledge-Grounded AI Research

SciAtlas is presented, a shared, machine-actionable cross-disciplinary scholarly knowledge infrastructure that integrates evidential, conceptual, disciplinary, expertise, and normative layers under a shared schema and achieves a unified neuro-symbolic retrieval mechanism that grounds heterogeneous research objects, pro...

Shuofei Qiao, Yun-Xiang Wei, Bu-Sheng Zhang et al. · 1 citation
Jul 2026

PRISM Edit: One Vector for All Temporal Answers

This work introduces PRISM Edit, which optimizes a single polysemous representation across temporal contexts and leverages the model's inherent modulation pathway to route it to temporally correct predictions without requiring any architectural modification.

Chen Huang, Qirui Zheng, Ruiqin Zheng et al. · 1 citation
Preprint Aug 2026

MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use

This work identifies memory-induced cognitive traps: even faithfully recorded and semantically relevant memories can distort model reasoning or beliefs and degrade current task performance, and proposes AdaptiveMem, a simple yet effective inference-time method that instructs LLMs to avoid memory traps.

Mengru Wang, Haozhe Luo, Zhen-Qiang Xu et al. · 0 citations
#artificial intelligence Preprint Sep 2025

OceanGym: A Benchmark Environment for Underwater Embodied Agents

OceanGym is introduced, the first comprehensive benchmark for ocean underwater embodied agents, designed to advance AI in one of the most demanding real-world environments, and reveals substantial gaps between state-of-the-art MLLM-driven agents and human experts.

Yida Xue, Mingjun Mao, Xiangyuan Ru et al. · 0 citations
#artificial intelligence Preprint Aug 2026

Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence

Mechanist is an agentic system that uses AI as a scientific instrument for the autonomous discovery of mechanisms underlying AI intelligence, and develops a mechanism theory of belief, revealing how models represent world knowledge, form beliefs, infer the beliefs of others, and how these mechanisms emerge during pretr...

Mengru Wang, Jun-Feng Fang, Shuo-Fei Qiao et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.