Enforcing Monotonic Progress in Legal Cross-Examination: Preventing Long-Horizon Stagnation in LLM-Based Inquiry

TL;DR

This paper introduces Soft-FSM, a neuro-symbolic architecture that enforces monotonic progress in LLM-based legal cross-examination, significantly improving task completion reliability by preventing procedural stagnation.

Contribution

The paper presents Soft-FSM, a novel external state controller that guarantees procedural progress in LLMs during complex legal inquiries, addressing a key limitation of probabilistic generation.

Findings

Baseline methods achieved less than 40% completeness.

Soft-FSM consistently achieved over 97% completeness.

Near-zero redundancy in the generated cross-examinations.

Abstract

Large language models (LLMs) exhibit impressive linguistic fluency but struggle to reliably complete long-horizon tasks under explicit procedural constraints. In legal cross-examination, purely proba-bilistic generation often maintains behavioral coherence while failing to ensure procedural advancement. We characterize this failure as procedural stagnation and propose Soft-FSM, a neuro-symbolic architecture that enforces monotonic progress over accumulated Key Information Units (KIUs) via an external deterministic state controller. Experiments on three real-world Taiwanese criminal homicide cases show that baseline methods collapse below 40% completeness, while Soft-FSM consistently achieves over 97% with near-zero redundancy. These results suggest that, in such domains, reliable task completion cannot be guaranteed by emergent LLM behavior alone, and can be reliably enforced through explicit and verifiable external state control.