ACL Findings2026
MASS: Deep Research for Social Sciences with Memory-Augmented Social Simulation
Abstract
Deep Research agents powered by Large Language Models (LLMs) have exhibited extraordinary potential in automated paper writing tasks. However, existing systems rely heavily on literature retrieval and synthesis through internet and local knowledge bases, often resulting research in lacking insight and creativity in social science. To address this issue, we propose "Memory-Augmented Social Simulation (MASS)", an innovative paradigm that leverages highly realistic and research-oriented social simulations to enhance the creativity and empirical founding of LLMs-generated research. Specifically, MASS integrates three core components: dynamic goal-path planning with multi-level social norm restraint to guide the simulation, a multi-disciplinary behavior dataset for agent memory cold-start, and a structured forgetting mechanism inspired by the Ebbinghaus curve. Together, these ensure simulation authenticity and provide a robust empirical foundation for generating innovative scholarly papers. Experimental results demonstrate the effectiveness of our method, showing a 6.81% improvement in generation overall quality over foundation LLMs and 17.19% gain in Insight over strong baselines. Dataset and codes will be released. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents cites DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments
- ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents cites Tree of Thoughts: Deliberate Problem Solving with Large Language Models
Builds on7
- Tree of Thoughts: Deliberate Problem Solving with Large Language ModelsShunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran et al.NeurIPS 2023 · 5,068 citations
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research AgentsMingxuan Du, Benfeng Xu, Chiwei Zhu, Licheng Zhang et al.ICLR 2026 · 250 citations
- ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue AgentsZhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao et al.ACL 2025 · 9 citations
- DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world EnvironmentsYuxiang Zheng, Dayuan Fu, Xiangkun Hu, Xiaojie Cai et al.EMNLP 2025 · 8 citations
- CToolEval: A Chinese Benchmark for LLM-Powered Agent Evaluation in Real-World API InteractionsZishan Guo, Yufei Huang, Deyi XiongACL Findings 2024 · 7 citations
Related papers
- NOVA: An Iterative Planning Framework for Enhancing Scientific Innovation with Large Language ModelsXiang Hu, Hongyu Fu, Jinge Wang, Yifeng Wang et al.ACL Findings 2025 · 3 citations
- Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular DataFengxian Dong, Zhi Zheng, Xiao Han, Wei Chen et al.ACL 2026
- Engagement-Driven Content Generation with Large Language ModelsErica Coppolillo, Federico Cinus, Marco Minici, Francesco Bonchi et al.KDD 2025 · 2 citations
- Mixture of Knowledge Minigraph Agents for Literature Review GenerationZhi Zhang, Yan Liu, Sheng-hua Zhong, Gong Chen et al.AAAI 2025 · 1 citation
- Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP ResearchersChenglei Si, Diyi Yang, Tatsunori HashimotoICLR 2025
