AIMAMay 12

Macro-Action Based Multi-Agent Instruction Following through Value Cancellation

arXiv:2605.1265548.4
Predicted impact top 74% in AI · last 90 daysOriginality Highly original
AI Analysis

Solves a fundamental failure mode in multi-agent instruction following for real-world applications requiring adaptive behavior.

MAVIC addresses value estimation inconsistency in MARL when natural language instructions interrupt macro-actions, achieving high instruction compliance while preserving base task performance in cooperative multi-agent environments.

Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and conflict with long-horizon objectives. However, conditioning rewards on instructions introduces a fundamental failure mode as Bellman updates couple value estimates across instruction contexts, leading to inconsistent values when instructions interrupt macro-actions. We propose Macro-Action Value Correction for Instruction Compliance (MAVIC), which corrects Bellman backups at instruction boundaries by correcting the incoming instruction objective and restoring the continuation value under the current objective. Unlike reward shaping, MAVIC modifies the bootstrapping target itself, enabling consistent value estimation under stochastic instruction switching within a unified policy. We provide theoretical analysis and an actor-critic implementation, and show that MAVIC achieves high instruction compliance while preserving base task performance in increasingly complex cooperative multi-agent environments.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes