Agentic AutoResearch forSpace Autonomy: An Auditable, LLM-Driven Research Agent for Aerospace Control Problems

2026-06-18

AI Summary

This work addresses the unreliability of learned policy evaluation in spacecraft guidance, navigation, and control due to stochastic seed noise by introducing AutoResearch—the first automated research framework that employs a large language model as an offline scientific agent. By interpreting natural language problem statements and experimental histories, AutoResearch autonomously modifies training scripts, executes experiments, and incorporates a tripartite audit mechanism—comprising seed-noise quantification, resampling validation, and leave-one-out edit pruning—to establish an auditable closed-loop research pipeline. Evaluated on Clohessy–Wiltshire rendezvous and proximity operations with no-fly zones, the audited policies significantly outperform noisy baselines; notably, in scenarios where conventional methods entirely fail, the proposed approach consistently satisfies safety constraints across all random seeds.

Abstract

Spacecraft guidance, navigation, and control functions are increasingly realized as learned policies distilled from expert solvers. Developing such a policy is itself a research process: an investigator selects an architecture and hyperparameters, runs experiments, and must determine whether an apparent improvement is genuine or merely seed noise. This paper presents AutoResearch, a framework in which a large language model autonomously drives that loop for aerospace control problems, coupled with a credibility layer, built into the loop, that certifies each reported result against the problem's own measured seed noise. The language model serves only as the offline research agent that develops the control policy; the trained policy it produces is then deployed onboard the spacecraft, while the model itself never operates the vehicle. At each iteration the agent reads a plain-language problem description and the run history, proposes a single edit to the training script, executes it, and logs the outcome. No reported result is credited until it passes the same three checks: measured per-problem seed noise, reseeded verification of the best configuration, and leave-one-out pruning of the agent's edits. The same loop is applied, unchanged, to two aerospace control problems: a Clohessy-Wiltshire relative rendezvous and a safety-constrained collision-avoidance docking past a keep-out zone, each calibrated against a known optimal control benchmark. In both, the audited policy clears the measured seed noise by many standard deviations; an undirected search over the same parameters does not. On the docking problem the gap becomes categorical: undirected search yields no feasible policy, while the learned policy stays outside the keep-out zone on every seed.

Problem

• space autonomy
• learned control policies
• seed noise
• policy validation
• aerospace control

Innovation

• AutoResearch
• LLM-driven research agent
• credibility layer
• seed noise auditing
• aerospace control