Controlling Long-Horizon Behavior in Language Model Agents with Explicit State Dynamics

• URL: http://arxiv.org/abs/2601.16087v1
• Date: Thu, 22 Jan 2026 16:34:05 GMT
• Title: Controlling Long-Horizon Behavior in Language Model Agents with Explicit State Dynamics
• Abstract summary: Large language model (LLM) agents exhibit abrupt shifts in tone and persona during extended interaction.<n>The role of explicit affective dynamics in shaping long-horizon agent behavior remains underexplored.<n>We introduce an agent-level affective subsystem that maintains a continuous Valence-Arousal-Dominance (VAD) state external to the language model.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language model (LLM) agents often exhibit abrupt shifts in tone and persona during extended interaction, reflecting the absence of explicit temporal structure governing agent-level state. While prior work emphasizes turn-local sentiment or static emotion classification, the role of explicit affective dynamics in shaping long-horizon agent behavior remains underexplored. This work investigates whether imposing dynamical structure on an external affective state can induce temporal coherence and controlled recovery in multi-turn dialogue. We introduce an agent-level affective subsystem that maintains a continuous Valence-Arousal-Dominance (VAD) state external to the language model and governed by first- and second-order update rules. Instantaneous affective signals are extracted using a fixed, memoryless estimator and integrated over time via exponential smoothing or momentum-based dynamics. The resulting affective state is injected back into generation without modifying model parameters. Using a fixed 25-turn dialogue protocol, we compare stateless, first-order, and second-order affective dynamics. Stateless agents fail to exhibit coherent trajectories or recovery, while state persistence enables delayed responses and reliable recovery. Second-order dynamics introduce affective inertia and hysteresis that increase with momentum, revealing a trade-off between stability and responsiveness.

Related papers

• Resilience: Understand Breakdown, Foster Recovery, and Choose the Right Perspective [1.2098798769432932]
  We distinguish between two different types of dynamics.<n>The first allows for a separation between phases of normalcy and phases of rapid breakdown followed by slow recovery.<n>The second applies to volatile organizations in which such phases are intertwined.
  arXiv  Detail & Related papers  (2026-07-28T08:48:19Z)
• How Affect Propagates among LLM Agents: Emergent Emotional Contagion in Crowd Simulation [0.0]
  We study how affect propagates among agents that perceive and appraise one another in a multi-agent crowd simulation.<n>The architecture contains no hand-authored mechanism for directly transferring affective state between agents.<n>We show that the system produces emotional contagion dynamics with spatial, temporal, and personality-dependent structure in sparse, small crowds.
  arXiv  Detail & Related papers  (2026-07-27T23:22:17Z)
• Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering [87.43777061308658]
  We analyze predictive behavior in full spoken language models (FDSLMs)<n>We show that FDSLMs dynamically modulate their internal focus between two states: a generative state aligned with model output generation and a perceptive state aligned incoming user input.<n>During user interruptions, the model remains transiently biased toward the generative state before transitioning into the perceptive state, causing it miss the beginning of incoming input.
  arXiv  Detail & Related papers  (2026-06-09T19:08:07Z)
• EgoMotion: Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation [74.07852250099559]
  We investigate Egocentric Vision-Language (Ego-VL) motion generation.<n>This task requires synthesizing 3D human motion conditioned jointly on first-person visual observations and natural language instructions.<n>We propose a hierarchical generative framework textbfEgoMotion to address this challenge.
  arXiv  Detail & Related papers  (2026-04-21T05:31:06Z)
• From Stateless to Situated: Building a Psychological World for LLM-Based Emotional Support [0.594744418467423]
  In psychological support and emotional companionship scenarios, the core limitation of large language models (LLMs) lies in their reliance on local next-token prediction.<n>We argue that the key challenge in process-oriented emotional support is not simply generating natural language, but constructing a sustainably updatable external situational structure for the model.
  arXiv  Detail & Related papers  (2026-03-26T04:54:24Z)
• State-Dependent Safety Failures in Multi-Turn Language Model Interaction [70.52906620450847]
  We study safety failures from a state-space perspective and show that many multi-turn failures arise from structured contextual state evolution.<n>We introduce STAR, a state-oriented diagnostic framework that treats dialogue history as a state transition operator.<n>We find that systems that appear robust under static evaluation can undergo rapid and reproducible safety collapse under structured multi-turn interaction.
  arXiv  Detail & Related papers  (2026-03-15T12:13:01Z)
• State Rank Dynamics in Linear Attention LLMs [37.607046806053035]
  State Rank Stratification is characterized by a distinct spectral bifurcation among linear attention heads.<n>Low-rank heads are indispensable for model reasoning, whereas high-rank heads exhibit significant redundancy.<n>We propose Joint Rank-Norm Pruning, a zero-shot strategy that achieves a 38.9% reduction in KV-cache overhead while largely maintaining model accuracy.
  arXiv  Detail & Related papers  (2026-02-02T15:00:42Z)
• Dynamical Systems Analysis Reveals Functional Regimes in Large Language Models [0.8694591156258423]
  Large language models perform text generation through high-dimensional internal dynamics.<n>Most interpretability approaches emphasise static representations or causal interventions, leaving temporal structure largely unexplored.<n>We discuss a composite dynamical metric, computed from activation time-series during autoregressive generation.
  arXiv  Detail & Related papers  (2026-01-11T21:57:52Z)
• Stable Language Guidance for Vision-Language-Action Models [62.80963701282789]
  Residual Semantic Steering is a probabilistic framework that disentangles physical affordance from semantic execution.<n> RSS achieves state-of-the-art robustness, maintaining performance even under adversarial linguistic perturbations.
  arXiv  Detail & Related papers  (2026-01-07T16:16:10Z)
• Emotion-Inspired Learning Signals (EILS): A Homeostatic Framework for Adaptive Autonomous Agents [0.0]
  This paper proposes that the unaddressed factor in robust autonomy is a functional analog to biological emotion, serving as a high-level homeostatic control mechanism.<n>We introduce Emotion-Inspired Learning Signals (EILS), a unified framework that replaces scattered optimizations with a coherent, bio-inspired internal feedback engine.
  arXiv  Detail & Related papers  (2025-12-20T19:46:51Z)
• Chronological Thinking in Full-Duplex Spoken Dialogue Language Models [66.84843878538207]
  Chronological Thinking aims to improve response quality in full SDLMs.<n>No additional latency: once the user stops speaking, the agent halts thinking and begins speaking without further delay.<n>Results: Experiments demonstrate the effectiveness of chronological thinking through both objective metrics and human evaluations.
  arXiv  Detail & Related papers  (2025-10-02T10:28:11Z)
• OmniReason: A Temporal-Guided Vision-Language-Action Framework for Autonomous Driving [6.136909494522169]
  We propose OmniReason, which establishes temporal reasoning by jointly modeling dynamic 3D environments.<n>We also develop the OmniReason-Agent architecture, which integrates temporal memory for scene context.
  arXiv  Detail & Related papers  (2025-08-31T10:34:44Z)
• MotionGPT3: Human Motion as a Second Modality [28.616340011811843]
  MotionGPT3 is a bimodal motion-language model for both understanding and generation.<n>A dual-stream Transformer with shared attention preserves modality-specific routes while enabling controlled, bidirectional information flow.<n>Experiments show that MotionGPT3 achieves 2x faster convergence in training loss and up to 4x faster convergence in validation.
  arXiv  Detail & Related papers  (2025-06-30T17:42:22Z)
• Neural Interaction Energy for Multi-Agent Trajectory Prediction [55.098754835213995]
  We introduce a framework called Multi-Agent Trajectory prediction via neural interaction Energy (MATE) MATE assesses the interactive motion of agents by employing neural interaction energy. To bolster temporal stability, we introduce two constraints: inter-agent interaction constraint and intra-agent motion constraint.
  arXiv  Detail & Related papers  (2024-04-25T12:47:47Z)
• Persistent-Transient Duality: A Multi-mechanism Approach for Modeling Human-Object Interaction [58.67761673662716]
  Humans are highly adaptable, swiftly switching between different modes to handle different tasks, situations and contexts. In Human-object interaction (HOI) activities, these modes can be attributed to two mechanisms: (1) the large-scale consistent plan for the whole activity and (2) the small-scale children interactive actions that start and end along the timeline. This work proposes to model two concurrent mechanisms that jointly control human motion.
  arXiv  Detail & Related papers  (2023-07-24T12:21:33Z)
• Model-Based Reinforcement Learning with Isolated Imaginations [61.67183143982074]
  We propose Iso-Dream++, a model-based reinforcement learning approach. We perform policy optimization based on the decoupled latent imaginations. This enables long-horizon visuomotor control tasks to benefit from isolating mixed dynamics sources in the wild.
  arXiv  Detail & Related papers  (2023-03-27T02:55:56Z)
• Isolating and Leveraging Controllable and Noncontrollable Visual Dynamics in World Models [65.97707691164558]
  We present Iso-Dream, which improves the Dream-to-Control framework in two aspects. First, by optimizing inverse dynamics, we encourage world model to learn controllable and noncontrollable sources. Second, we optimize the behavior of the agent on the decoupled latent imaginations of the world model.
  arXiv  Detail & Related papers  (2022-05-27T08:07:39Z)

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.