Towards Operationalizing Accountability for Self-Improving Multi-Agent Systems

AAMAS 2026 Workshop EMAS Submission52 Authors

Keywords: Accountability, Self-Improving Multi-Agent Systems, Large Language Models

TL;DR: This paper presents ongoing work on accountability mechanisms that enable agents to learn from suboptimal outcomes by updating their skills through LLM-mediated account evaluation and feedback.

Abstract: Accountability mechanisms can help agents improve their behavior by learning from substandard outcomes. When a substandard situation arises, an accountee requests accountors to render accounts, evaluates them to derive remedies, and provides feedback that accountors use to update their procedural knowledge. We present ongoing work on designing such mechanisms for self-improving multi-agent systems. Our current focus is on agents equipped with skills created by developers, where the objective is to enable agents to improve these skills over time. Accountors render accounts in natural language, and we use LLMs to evaluate accounts, provide feedback, and update skills based on this feedback. We present a JaCaMo-based implementation for a home heating scenario where an agent wastes energy heating a room with a tilted window. Preliminary experiments with Claude Opus 4.5 show promising results: the agent learns preventive behaviors (checking and closing the window before heating) in 90% of cases and corrective behaviors (closing the window during heating) in 90% of cases. We extend our experiments to include a human accountor who intentionally left the window open for a bird to fly out. In this scenario, the agent learns to respect the human's intention (stopping or delaying the heating without closing the window) in 80% of prescriptive and 40% of corrective cases. The agent also learns to resume heating once the human closes the window in 40% of cases. These results show that using accountability for self-improvement transcends debugging, enabling collaborative behaviors that respect human intentions.

Paper Type: Short paper

Demo: Yes, we would love to present a demo.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 52