2 papers
cs.AI2026
FARL: A Fully Automated Pipeline of RL Interface and Solver Design
Tianyu Jin, Liuyu Xiang, Chaowen Yang +3
Existing reinforcement learning (RL) largely focuses on optimizing learning algorithms within a pre-defined task formulation, while applying RL to new tasks still relies heavily on…
cs.CR2026
Poisoned into Action: Context Attacks on Typed Decision Workflows
Chenkai Wu, Xing Chang, Jun Yan
Typed decision interfaces restrict models to predefined actions, yet schema-valid choices can still trigger policy-violating state changes. Evaluating context poisoning thus requir…