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

• URL: http://arxiv.org/abs/2608.06975v1
• Date: Fri, 07 Aug 2026 08:50:14 GMT
• Title: PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue
• Abstract summary: PHASE-Tree is a multi-timescale character-state tree with an immutable identity root and mutable persona, session, and moment layers.<n>It conditions generation through explicit textual provision or implicit parametric adaptation.<n>On the long-dialogue core, PHASE-Tree ranks first in 11 of 12 dataset-metric cells against internal variants and all 12 cells against external textual baselines.
• Score: 37.64180837016861
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Creating an Atomic User Model for Personality-Aware Large Language Model Interaction [0.0]
  Atomic User Model (AUM) is a human-readable representation organising a person as a stable identity nucleus.<n>A pipeline where a task classifier, component-selection function and budgeted retriever return a small payload of fields at generation time.<n>Retrieving eight fields matched the style fidelity of the full user model on 23% of the context.
  arXiv  Detail & Related papers  (2026-09-10T18:11:43Z)
• A Three-Tier Persona Vector for Controllable User Simulation in Agentic Evaluation [0.9918136378822991]
  We propose a three-tier persona vector with 23 operationalized dimensions.<n>We evaluate the persona model inside a synthetic data generation pipeline across 64,698 conversations.
  arXiv  Detail & Related papers  (2026-09-08T11:28:02Z)
• Beyond Individual Personas: Aligning Synthetic Dialogue to Population-Level Behavior Distributions [21.099809383806598]
  GroupPersona is a framework that aligns synthetic dialogue corpora to the behavior distribution of a reference corpus.<n>It separates each dialogue's core behavioral signature from predictable side effects, and uses the resulting behavioral groups to condition user agents on the interaction patterns that define the reference population.
  arXiv  Detail & Related papers  (2026-06-05T23:03:53Z)
• HorizonBench: Long-Horizon Personalization with Evolving Preferences [73.32940850193681]
  We introduce a data generator that produces conversations from a structured mental state graph.<n>From it construct HorizonBench, a benchmark of 4,245 items from 360 simulated users with 6-month conversation histories.<n> HorizonBench provides a testbed for long-context modeling, memory-augmented architectures, theory-of-mind reasoning, and user modeling.
  arXiv  Detail & Related papers  (2026-04-19T06:55:10Z)
• Dynamic Context Evolution for Scalable Synthetic Data Generation [0.0]
  Large language models produce repetitive output when prompted independently across many batches.<n>We introduce Dynamic Context Evolution (DCE), comprising three mechanisms.<n>DCE reconstructs the generation prompt each batch using memory state and rotating diversity strategies.
  arXiv  Detail & Related papers  (2026-04-08T14:38:11Z)
• ClawArena: Benchmarking AI Agents in Evolving Information Environments [61.664633997138004]
  ClawArena is a benchmark for evaluating AI agents in evolving information environments.<n>Each scenario maintains a complete hidden ground truth while exposing the agent only to noisy, partial, and sometimes contradictory traces.<n> evaluation is organized around three coupled challenges: multi-source conflict reasoning, dynamic belief revision, and implicit personalization.
  arXiv  Detail & Related papers  (2026-04-05T17:55:23Z)
• PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environments [72.02445514666428]
  We introduce PERMA, a benchmark designed to evaluate persona consistency over time beyond static preference recall.<n>PerMA consists of temporally ordered interaction events spanning multiple sessions and domains, with preference-related queries inserted over time.<n> Experiments demonstrate that by linking related interactions, advanced memory systems can extract more precise preferences and reduce token consumption.
  arXiv  Detail & Related papers  (2026-03-24T14:04:11Z)
• From Word Sequences to Behavioral Sequences: Adapting Modeling and Evaluation Paradigms for Longitudinal NLP [10.614902538213638]
  We show that document-level evaluation can yield substantially different and sometimes reversed conclusions compared to our ecologically valid modeling and evaluation.<n>We tie our results to a broader discussion motivating a shift from word-sequence evaluation toward $textitbehavior-sequence$ paradigms for NLP.
  arXiv  Detail & Related papers  (2026-01-12T20:38:36Z)
• Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents [80.33280979339123]
  We introduce Memory-T1, a framework that learns a time-aware memory selection policy using reinforcement learning (RL)<n>On the Time-Dialog benchmark, Memory-T1 boosts a 7B model to an overall score of 67.0%, establishing a new state-of-the-art performance for open-source models.
  arXiv  Detail & Related papers  (2025-12-23T06:37:29Z)
• X-TURING: Towards an Enhanced and Efficient Turing Test for Long-Term Dialogue Agents [56.64615470513102]
  The Turing test examines whether AIs exhibit human-like behaviour in natural language conversations.<n>Traditional setting limits each participant to one message at a time and requires constant human participation.<n>This paper proposes textbftextscX-Turing, which enhances the original test with a textitburst dialogue pattern.
  arXiv  Detail & Related papers  (2024-08-19T09:57:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.