PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue

2026-08-07

AI Summary

Existing role-playing dialogue systems struggle to dynamically evolve character states over long-form narratives while maintaining consistency, and lack benchmarks for evaluating such evolutionary generation capabilities. This work proposes PHASE-Tree, a multi-timescale hierarchical character state representation structured as a tree with an immutable identity root and mutable layers encompassing personality, conversational memory, and transient states. The framework supports localized cross-session updates and guides response generation through either explicit textual injection or implicit parameter adaptation. We introduce the first character state representation framework enabling partial updates and release LongEvoRoleBench, a new evaluation benchmark. Experiments show that PHASE-Tree significantly outperforms baselines across all 12 metrics, achieving improvements of 19.7%, 12.4%, and 15.1% in character-level, semantic, and embedding scores, respectively, with human preferences strongly correlating with GPT-4.1 evaluations (r = 0.65).

Abstract

Long-horizon role-playing demands that characters remain recognizable as they evolve with the narrative. Yet existing work falls short on two fronts: representations are typically static profiles that cannot be updated locally without destabilizing unchanged traits, and benchmarks mainly test persona preservation and memory recall rather than whether a model speaks from a character's currently evolved state. We address both. PHASE-Tree is a multi-timescale character-state tree with an immutable identity root and mutable persona, session, and moment layers, making each mutable field an addressable target for localized within- and cross-episode updates. It conditions generation through explicit textual provision or implicit parametric adaptation. To measure evolved-state generation, we introduce LongEvoRoleBench, which pairs four long-dialogue corpora for cross-episode evolution with four short-dialogue corpora as within-scene state-tracking checks, under a unified next-utterance protocol. On the long-dialogue core, textual PHASE-Tree ranks first in 11 of 12 dataset-metric cells against internal variants and all 12 cells against external textual baselines, improving character-level, semantic, and embedding scores by 19.7%, 12.4%, and 15.1% respectively. In a blinded 200-response study, human ratings correlate with the GPT-4.1 judge (Pearson r= 0.65); on descriptive n= 10 PT and NR prompt subsets, the Overall difference is +0.20. The long-dialogue Sem advantage persists across LLM judges and generation backbones.

Problem

• character-state evolution
• long-horizon dialogue
• role-playing
• persona consistency
• state tracking

Innovation

• PHASE-Tree
• character-state evolution
• multi-timescale modeling
• LongEvoRoleBench
• role-playing dialogue