2 papers
cs.LG2026
Can LLM Safety Be Ensured by Constraining Parameter Regions?
Zongmin Li, Jian Su, Farah Benamara +1
Large language models (LLMs) are often assumed to contain ``safety regions'' -- parameter subsets whose modification directly influences safety behaviors. We conduct a systematic e…
cs.CL2026
Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization
Jianghao Su, Xia Zeng, Luhui Liu +3
Large Language Models (LLMs) empowered with Tool-Integrated Reasoning (TIR) can iteratively plan, call external tools, and integrate returned information to solve complex, long-hor…