paper-with-me

홈 › Papers

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

2026-01-22 · Sukesh Subaharan arxiv

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.

📄 PDF Abstract BibTeX arXiv:2601.16087

Code (0)

등록된 구현이 없습니다.

Tasks

Emotion Classification

Similar Papers 제목 키워드 기반

The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems Break

2026-04-13 · Xinyu Jessica Wang, Haoyue Bai, Yiyou Sun, Haorui Wang 외 arxiv

Large language model (LLM) agents perform strongly on short- and mid-horizon tasks, but often break down on long-horizon tasks that require extended, interdependent action sequences. Despite rapid progress in agentic sys…

RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments

2026-06-14 · Linghua Zhang, Jun Wang, Jingtong Wu, Zhisong Zhang arxiv

Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailB…

Decision Making

Step-Level Preference Learning for Generative Agents in Social Simulations

2026-07-16 · Wenchang Gao, Pingyue Sheng, Lanlan Qiu, Yunfei Ma 외 arxiv

Large language model (LLM)-based generative agents simulate human behavior through long-horizon decision-making processes that comprise intermediate steps such as planning, memory retrieval, reflection, and action select…

RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments

2026-03-17 · Linghua Zhang, Jun Wang, Jingtong Wu, Zhisong Zhang arxiv

Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailB…

Decision Making

Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents

2026-01-29 · Zehong Wang, Fang Wu, Hongru Wang, Xiangru Tang 외 arxiv

Large language model (LLM)-based agents exhibit strong step-by-step reasoning capabilities over short horizons, yet often fail to sustain coherent behavior over long planning horizons. We argue that this failure reflects…

Decision Making