AtomMem: Learnable Dynamic Agentic Memory with Atomic Memory Operation
EMNLP 2026 (CCF-B). Supervisor. Learnable dynamic agentic memory built from atomic memory operations.
yupeng-huo
•
•
1 分钟阅读时长
Test-Time Deep Thinking to Explore Implicit Rules
KDD 2026 (CCF-A). Co-corresponding author. Test-time deep thinking that infers implicit environment rules to guide agent exploration.
wentong-chen
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
KDD 2026 (CCF-A). A benchmark for diagnosing step-level process quality in tool-using agents.
shengda-fan
AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning
EMNLP 2025 Demo. GUI agents with reinforcement fine-tuning. 1,400+ GitHub Stars.
zhong-zhang
RD2Bench: Toward Data-Centric Automatic R&D
ICLR 2024 Workshop. First author. RD2Bench / RD-Agent for data-centric automatic R&D. Featured in the Microsoft Build 2025 keynote; 15,100+ GitHub Stars.
OODREB: Benchmarking State-of-the-Art Methods for Out-Of-Distribution Generalization on Relation Extraction
**CCF-A**. Benchmarking OOD generalization methods for relation extraction.
Rethinking the Development of Large Language Models from the Causal Perspective: A Legal Text Prediction Case Study
**CCF-A**. Rethinking LLM development from the causal perspective with a legal text prediction case study.
SALAS: Supervised Aspect Learning Improves Abstractive Multi-Document Summarization through Aspect Information Loss
**CCF-B**. Supervised aspect learning for multi-document summarization.
Did the Models Understand Documents? Benchmarking Models for Language Understanding in Document-Level Relation Extraction
**CCF-A**. Benchmarking language understanding models for document-level relation extraction.
Recovering Missing Key Information: An Aspect-guided Generator for Abstractive Multi-document Summarization
**CCF-B**. Aspect-guided generator for abstractive multi-document summarization.