2 papers
cs.LG2026
Predictive Divergence Masks for LLM RL
Xiangxin Zhou, Jiarui Yao, Penghui Qi +4
Reinforcement learning for large language models (LLMs) typically relies on trust-region masks to stabilize off-policy updates. The dominant PPO-style approach uses the sampled-tok…
cs.LG2026
Self-Evolution for Multi-Turn Tool-Calling Agents via Divergence-Point Preference Learning
Jiaqiang Tang
Multi-turn tool-using agents must coordinate long-horizon tool sequences while tracking dialogue state and policy constraints. Existing approaches often separate inference-time orc…