3 papers
cs.LG2026
ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
Zihan Lin, Xiaohan Wang, Jie Cao +6
Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivi…
cs.CL2026
MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
Tianyu Hu, Weikai Lin, Weizhi Zhang +2
Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every turn to make that decision. W…
cs.CL2025
Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning
Yongquan He, Wenyuan Zhang, Xuancheng Huang +5
Instruction tuning for large language models (LLMs) can drive them to produce results consistent with human goals in specific downstream tasks. However, the process of continual in…