Environment Steering: Using Data Flow Control to Improve Agent Utility and Safety
LLM agents can make unsafe tool calls even when instructed to behave safely. Existing defenses constrain agents before execution, modify tool inputs/outputs, or rely on LLM judges; these approaches may depend on model behavior or block unsafe actions without helping the agent recover. We argue that the execution enviro...
Charlie Summers, Prajwal Raghunath, Aaditya Pai et al.
· 0 citations