2 papers
cs.CL2026
Propose, Verify, Commit: Evidence-Grounded Memory for Long-Horizon Multi-Actor Conversations
Zihao Lu, Zhihang Yuan, Lei Shi +1
Memory enables language model agents to use information beyond their context windows, but maintaining and accessing this information reliably remains difficult. Long-horizon conver…
cs.CL2026
Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning
Zhihang Yuan, Chengyu Yue, Long Huang +2
Instruction tuning is a standard paradigm for adapting large language models (LLMs), but modern instruction datasets are large, noisy, and redundant, making full-data fine-tuning c…