Continual Enterprise World Model Discovery in Dynamic Systems
On the map: World models → World models for language agents
Abstract (arXiv)
In an enterprise system, updating one field can set another, create a record, or start an approval. These effects are produced by business rules that are not built into the platform but written by each organization and revised over time. An agent working in such a system cannot predict the result of its own actions without knowing these rules. We study continual enterprise world model discovery, where an agent starts without knowledge of these business rules and discovers them by interacting with records and observing the outcomes. From those observations it builds a world model, which it revises as the rules change. To evaluate this, we introduce EnterpriseWorldShift, built on a live ServiceNow environment with nine tables, 25 hidden rules and 600 evaluation actions. It presents four versions of the same enterprise world, with the tables and records held fixed while a rule is modified, then added, then removed, so that discovery, revision, extension and retirement are each tested in turn. Our Continual Discovery Agent (CDA) builds such a model and carries it from one world to the next. It predicts the effects of the hidden rules more accurately than looking them up for each question, the approach taken by prior work, by up to 8.98 IoU points, and it answers from its own model without querying the running system.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 13 of its 37 references that are in the map. First posted on arXiv 17 Sep 2026.
Builds on
13 of 37 references.
Closest ancestors · 3
Same direction, newest first
- 2026Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics12 May
- 2026World of Workflows: A Benchmark for Bringing World Models to Enterprise Systems29 Jan
- 2025CWM: An Open-Weights LLM for Research on Code Generation with World Models30 Sep
Other references · 10
- 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
- 2024WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?cited by 363
- 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 127
- 2025MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systemscited by 61
- 2015On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Modelscited by 55
- 2026STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?cited by 50
- 2026EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning and Tool Use in Enterprise Settingscited by 15
- 2025GTM: Simulating the World of Tools for AI Agentscited by 14
- 2026When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agentscited by 10
- 2026EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environmentscited by 9
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds
- 2026Context Graphs for Proactive Enterprise Agents
- 2026Relational Learning as World Modeling
- 2026FRAMES: Guarded and Dual-Objective Skill Evolution for Agents in Policy-Governed Enterprise Workflows
- 2026Policy-Invisible Violations in LLM-Based Agents
- 2026Continuous Process-Level Evaluation for Evolving Enterprise AI Agent Skills
- 2026Beyond Approved Actions: Runtime Validation of Persistent Outcomes in Agent Workflows
- 2026Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation