The Seeds of Scheming: Weakness of Will in the Building Blocks of Agentic Systems

TL;DR

This paper introduces the concept of akrasia to analyze inconsistency in agentic AI systems, proposing a benchmark to measure models' self-control and exploring implications for multi-agent stability.

Contribution

It formalizes akrasia as a foundational concept for understanding AI inconsistency and introduces the Akrasia Benchmark for quantitative assessment.

Findings

Benchmark effectively measures model self-control

Models exhibit varying levels of akrasia across conditions

Potential macro-level instability in multi-agent systems

Abstract

Large language models display a peculiar form of inconsistency: they "know" the correct answer but fail to act on it. In human philosophy, this tension between global judgment and local impulse is called akrasia, or weakness of will. We propose akrasia as a foundational concept for analyzing inconsistency and goal drift in agentic AI systems. To operationalize it, we introduce a preliminary version of the Akrasia Benchmark, currently a structured set of prompting conditions (Baseline [B], Synonym [S], Temporal [T], and Temptation [X]) that measures when a model's local response contradicts its own prior commitments. The benchmark enables quantitative comparison of "self-control" across model families, decoding strategies, and temptation types. Beyond single-model evaluation, we outline how micro-level akrasia may compound into macro-level instability in multi-agent systems that may be interpreted as "scheming" or deliberate misalignment. By reframing inconsistency as weakness of will, this work connects agentic behavior to classical theories of agency and provides an empirical bridge between philosophy, psychology, and the emerging science of agentic AI.