5 papers
EvoGraph-Mem: Failure-Aware Editable Graph Memory for Long-Term Language Agents
Yuxi Qian, Yuxiang Ren
Long-term memory is essential for language agents operating across extended interactions and evolving tasks. Existing memory-augmented agents mainly focus on storing and retrieving…
Graph2Eval: Automatic Multimodal Task Generation for Agents via Knowledge Graphs
Yurun Chen, Xavier Hu, Yuhan Liu +8
As multimodal LLM-driven agents advance in autonomy and generalization, traditional static datasets face inherent scalability limitations and are insufficient for fully assessing t…
I-MCTS: Enhancing Agentic AutoML via Introspective Monte Carlo Tree Search
Zujie Liang, Feng Wei, Wujiang Xu +3
Recent advancements in large language models (LLMs) have shown remarkable potential in automating machine learning tasks. However, existing LLM-based agents often struggle with low…
Towards Adaptive ML Benchmarks: Web-Agent-Driven Construction, Domain Expansion, and Metric Optimization
Hangyi Jia, Yuxi Qian, Hanwen Tong +3
Recent advances in large language models (LLMs) have enabled the emergence of general-purpose agents for automating end-to-end machine learning (ML) workflows, including data analy…
SEGMENT+: Long Text Processing with Short-Context Language Models
Wei Shi, Shuang Li, Kerun Yu +9
There is a growing interest in expanding the input capacity of language models (LMs) across various domains. However, simply increasing the context window does not guarantee robust…