Narrative World Model: Narratology-Grounded Writer Memory for Long-Form Fiction

Authors: Mohammad Saifullah, Thomas Kornmaier, Taaha Kazi, Vasu Sharma, Aditya Sanjiv Kanade, Aanand Kumar Yadav

Abstract: Long-form fiction writers need memory that answers multi-hop questions about evolving story state: who knows a secret and when they learned it, whether an event preceded the narration that revealed it, whether a setup paid off, and how a relationship shifted. General-purpose retrieval and agent-memory systems represent entities and facts but not the narratological structure these questions turn on… ▽ More Long-form fiction writers need memory that answers multi-hop questions about evolving story state: who knows a secret and when they learned it, whether an event preceded the narration that revealed it, whether a setup paid off, and how a relationship shifted. General-purpose retrieval and agent-memory systems represent entities and facts but not the narratological structure these questions turn on, so they surface the wrong evidence or none at all. We introduce the Narrative World Model (NWM), a writer-memory system that pairs a narratology-grounded typed temporal-state graph with query-conditioned hybrid retrieval. To measure memory rather than the answerer, we read every system through a single held-constant Opus 4.8 reader over only that system's chapter-safe evidence, on a reproducible public corpus and a validated multi-hop benchmark, and we compare against the strongest existing temporal-knowledge-graph agent-memory framework, Graphiti/Zep (Rasmussen et al., 2025). NWM substantially and significantly outperforms this baseline on multi-hop narratological QA across both corpora, and far exceeds GraphRAG and flat retrieval. The advantage is representational rather than an artifact of extraction: it survives rebuilding the baseline with NWM's own extractor, and traces to its narratology-grounded structure and query-conditioned retrieval, not to graph size or extractor quality. △ Less

Submitted 6 July, 2026; originally announced July 2026.

NarrativeWorldBench: A Frontier-Saturated Benchmark and a Latent World Model for Long-Horizon Co-Creative Audio Drama

Authors: Logan Mann, Abdur Rahman, Mohammad Saifullah, Taaha Kazi, Vasu Sharma

Abstract: Long-form serialized audio drama, with arcs that run for 200 to 800 episodes, is a major creative medium and a setting where frontier large language models (LLMs) fail. We benchmark 21 models, spanning classical, fine-tuned, open-frontier, closed-frontier, and reasoning tiers, on a uniform set of structural narrative metrics. All closed-frontier systems saturate at a plot-beat F1 in the band [0.78… ▽ More Long-form serialized audio drama, with arcs that run for 200 to 800 episodes, is a major creative medium and a setting where frontier large language models (LLMs) fail. We benchmark 21 models, spanning classical, fine-tuned, open-frontier, closed-frontier, and reasoning tiers, on a uniform set of structural narrative metrics. All closed-frontier systems saturate at a plot-beat F1 in the band [0.78, 0.81] and collapse by about -0.20 F1 at horizon h=200. We introduce NarrativeWorldBench, an open benchmark of nine narrative-structure metrics evaluated across horizons h in {10, 20, 50, 100, 200}, with cross-lingual evaluation across four Indic languages (Hindi, Tamil, Telugu, Marathi). We introduce N-VSSM, a Narrative Variational State-Space Model that maintains a structured 256-dimensional latent world state over more than 200 episodes via a Mamba-2 backbone with an event-conditioned posterior and an 8B decoder. N-VSSM holds plot-beat F1 >= 0.84 across all horizons at 4x lower compute than the closed-frontier band. A learned Cultural Transfer Function lifts cross-language fidelity by +0.20 to +0.23 Likert points. In a within-subjects writer study (n = 12 professional authors, 240 trials), N-VSSM is preferred over Claude Opus 4.5 on long-arc consistency 71% of the time and rated +1.3 Likert points higher on controllability. △ Less

Submitted 15 June, 2026; originally announced June 2026.

Multi-agent deep reinforcement learning with centralized training and decentralized execution for transportation infrastructure management

Authors: M. Saifullah, K. G. Papakonstantinou, A. Bhattacharya, S. M. Stoffels, C. P. Andriotis

Abstract: Life-cycle management of large-scale transportation systems requires determining a sequence of inspection and maintenance decisions to minimize long-term risks and costs while dealing with multiple uncertainties and constraints that lie in high-dimensional spaces. Traditional approaches have been widely applied but often suffer from limitations related to optimality, scalability, and the ability t… ▽ More Life-cycle management of large-scale transportation systems requires determining a sequence of inspection and maintenance decisions to minimize long-term risks and costs while dealing with multiple uncertainties and constraints that lie in high-dimensional spaces. Traditional approaches have been widely applied but often suffer from limitations related to optimality, scalability, and the ability to properly handle uncertainty. Moreover, many existing methods rely on unconstrained formulations that overlook critical operational constraints. We address these issues in this work by casting the optimization problem within the framework of constrained Partially Observable Markov Decision Processes (POMDPs), which provide a robust mathematical foundation for stochastic sequential decision-making under observation uncertainties, in the presence of risk and resource limitations. To tackle the high dimensionality of state and action spaces, we propose DDMAC-CTDE, a Deep Decentralized Multi-Agent Actor-Critic (DDMAC) reinforcement learning architecture with Centralized Training and Decentralized Execution (CTDE). To demonstrate the utility of the proposed framework, we also develop a new comprehensive benchmark environment representing an existing transportation network in Virginia, U.S., with heterogeneous pavement and bridge assets undergoing nonstationary degradation. This environment incorporates multiple practical constraints related to budget limits, performance guidelines, traffic delays, and risk considerations. On this benchmark, DDMAC-CTDE consistently outperforms standard transportation management baselines, producing better policies. Together, the proposed framework and benchmark provide (i) a scalable, constraint-aware methodology, and (ii) a realistic, rigorous testbed for comprehensive evaluation of Deep Reinforcement Learning (DRL) for transportation infrastructure management. △ Less

Submitted 24 February, 2026; v1 submitted 22 January, 2024; originally announced January 2024.

Design of Adiabatic MTJ-CMOS Hybrid Circuits

Authors: Fazel Sharifi, Z. M. Saifullah, Abdel-Hameed Badawy

Abstract: Low-power designs are a necessity with the increasing demand of portable devices which are battery operated. In many of such devices the operational speed is not as important as battery life. Logic-in-memory structures using nano-devices and adiabatic designs are two methods to reduce the static and dynamic power consumption respectively. Magnetic tunnel junction (MTJ) is an emerging technology wh… ▽ More Low-power designs are a necessity with the increasing demand of portable devices which are battery operated. In many of such devices the operational speed is not as important as battery life. Logic-in-memory structures using nano-devices and adiabatic designs are two methods to reduce the static and dynamic power consumption respectively. Magnetic tunnel junction (MTJ) is an emerging technology which has many advantages when used in logic-in-memory structures in conjunction with CMOS. In this paper, we introduce a novel adiabatic hybrid MTJ/CMOS structure which is used to design AND/NAND, XOR/XNOR and 1-bit full adder circuits. We simulate the designs using HSPICE with 32nm CMOS technology and compared it with a non-adiabatic hybrid MTJ/CMOS circuits. The proposed adiabatic MTJ/CMOS full adder design has more than 7 times lower power consumtion compared to the previous MTJ/CMOS full adder. △ Less

Submitted 25 August, 2017; originally announced August 2017.