1 citations · 1 across the 6 of their papers we have counts for
7 papers
MemHarness: Memory Is Reconstructed, Not Replayed
Rong Wu, Daocheng Fu, Licheng Wen +10
Retrieving past experiences has become a common strategy to enhance large language model agents. However, most existing memory-augmented agents treat retrieved experiences as stati…
Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger
Wenjun Li, Dexun Li, Kuicai Dong +6
Large language models (LLMs) have shown remarkable emergent capabilities, transforming the execution of functional tasks by leveraging external tools for complex problems that requ…
Rank Aggregation in Crowdsourcing for Listwise Annotations
Wenshui Luo, Haoyu Liu, Yongliang Ding +7
Rank aggregation through crowdsourcing has recently gained significant attention, particularly in the context of listwise ranking annotations. However, existing methods primarily f…
CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
Huanshuo Liu, Hao Zhang, Zhijiang Guo +6
Retrieval-augmented generation (RAG) has emerged as a promising solution for mitigating hallucinations of large language models (LLMs) with retrieved external knowledge. Adaptive R…
Planning with Multi-Constraints via Collaborative Language Agents
Cong Zhang, Derrick Goh Xin Deik, Dexun Li +2
The rapid advancement of neural language models has sparked a new surge of intelligent agent research. Unlike traditional agents, large language model-based agents (LLM agents) hav…
Multi-view Content-aware Indexing for Long Document Retrieval
Kuicai Dong, Derrick Goh Xin Deik, Yi Quan Lee +4
Long document question answering (DocQA) aims to answer questions from long documents over 10k words. They usually contain content structures such as sections, sub-sections, and pa…
Aligning Crowd Feedback via Distributional Preference Reward Modeling
Dexun Li, Cong Zhang, Kuicai Dong +3
Deep Reinforcement Learning is widely used for aligning Large Language Models (LLM) with human preference. However, the conventional reward modelling is predominantly dependent on…