A Signal Contract for Online Language Grounding and Discovery in Decision-Making

TL;DR

This paper introduces LUCIFER, a middleware framework for online language grounding in autonomous decision-making, enabling robust, domain-agnostic interpretation of natural language updates during task execution.

Contribution

The paper presents LUCIFER, a novel inference-only middleware that provides a Signal Contract for converting verbal reports into control signals, improving robustness and flexibility in dynamic environments.

Findings

LUCIFER maintains robust reasoning-based extraction on self-correcting reports.

System-level evaluations show the importance of grounding and discovery for safety and efficiency.

The framework is effective across different client architectures, demonstrating versatility.

Abstract

Autonomous systems increasingly receive time-sensitive contextual updates from humans through natural language, yet embedding language understanding inside decision-makers couples grounding to learning or planning. This increases redeployment burden when language conventions or domain knowledge change and can hinder diagnosability by confounding grounding errors with control errors. We address online language grounding where messy, evolving verbal reports are converted into control-relevant signals during execution through an interface that localises language updates while keeping downstream decision-makers language-agnostic. We propose LUCIFER (Language Understanding and Context-Infused Framework for Exploration and Behavior Refinement), an inference-only middleware that exposes a Signal Contract. The contract provides four outputs, policy priors, reward potentials, admissible-option constraints, and telemetry-based action prediction for efficient information gathering. We validate LUCIFER in a search-and-rescue (SAR)-inspired testbed using dual-phase, dual-client evaluation: (i) component benchmarks show reasoning-based extraction remains robust on self-correcting reports where pattern-matching baselines degrade, and (ii) system-level ablations with two structurally distinct clients (hierarchical RL and a hybrid A*+heuristics planner) show consistent necessity and synergy. Grounding improves safety, discovery improves information-collection efficiency, and only their combination achieves both.