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

arXiv: https://arxiv.org/abs/2602.04206 · HTML: https://mlsanity.com/paper/2602.04206/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 11 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 6 of 6)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks](https://mlsanity.com/paper/2503.09572/) (2025)
- [The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs](https://mlsanity.com/paper/2509.09677/) (2025)
- [AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents](https://mlsanity.com/paper/2408.08089/) (2024)
- [Drift No More? Context Equilibria in Multi-Turn LLM Interactions](https://mlsanity.com/paper/2510.07777/) (2025)

## Built on by (most cited first, 1 of 1)

- [Harness as an Asset: Enforcing Determinism via the Convergent AI Agent Framework (CAAF)](https://mlsanity.com/paper/2604.17025/) (2026)

## Abstract (arXiv)

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.