B-PASTE: Beam-Aware Pattern-Guided Speculative Execution for Resource-Constrained LLM Agents

arXiv:2604.16469v1 Announce Type: cross Abstract: LLM agents execute in an interleaved reasoning-and-action loop, where future tool calls cannot be launched until the current reasoning step completes. This serial dependency inflates end-to-end latency and leaves the model idle while waiting for tool execution. Prior work, Pattern-Aware Speculative Tool Execution (PASTE), mitigates this bottleneck by speculating likely future tool invocations from mined control-flow and data-flow regularities. Ho