mlsanityData to 7 Oct 2026

TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized Views

arXiv 2607.21910 ↗First posted 24 Jul 2026cs.AI cs.DBcited by 0

On the map: World models → World models for language agents

Abstract (arXiv)

World models let agents plan against predicted physical state, but that state drifts; re-observation is costly and delayed, and repair can fail. We present TRACE-RealWorld (TRW), to our knowledge the first commitment-level consistency contract for world models. TRW treats predicted state as a materialized view and a physical commitment as a read whose authorization can expire. Typed, calibrated claims specify consequence-conditioned freshness and priced verification. Adaptive refresh generalizes dual-Kalman synchronization to consult the world when evidence could change a decision; dependency-scoped SagaLLM compensation repairs reversible commitments invalidated after authorization. Under an event-aligned risk oracle and recovery-liveness assumptions, we prove that synchronization and compensation are insufficient alone, whereas their composition gives a conditional consistency guarantee. Otherwise, the argument yields an auditable decomposition of violations into named debts. We implement TRW in Flood-SAR, a search-and-rescue simulator over real geography, and test six preregistered questions at frozen operating points on held-out seeds. Adaptive refresh reduces stale execution but does not dominate fixed refresh on cost, coverage, or rescue outcomes. Localized repair reduces repair work by 9.56 units per mission and restoration latency by 80.7 seconds relative to global recovery; the observed residual-violation difference is zero without establishing equivalence. Detection coverage is 0.83-0.89, and 10 of 97 invoked restorations are incomplete by mission end. The campaign treats empirical slack as sensitivity inputs rather than discharging the theorem's assumptions or providing a simultaneous population certificate. Exact replay reconstructs a disputed dispatch. TRW thus makes a world model an auditable predictive interface rather than a self-validating source of truth.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 9 of its 43 references that are in the map. First posted on arXiv 24 Jul 2026.

Builds on

9 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Cosmos World Foundation Model Platform for Physical AI7 Jan

Other references · 8

  1. 2023Mastering Diverse Domains through World Modelscited by 1,193
  2. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
  3. 2025Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robotscited by 15
  4. 2026Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflowscited by 8
  5. 2026Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rolloutscited by 4
  6. 2026Trivium: Temporal Regret as a First-Class Objective for Causal-Memory Controllerscited by 4
  7. 2026Digital Twin Synchronization: towards a data-centric architecturecited by 1
  8. 2026Certified World Models as Sensing Clocks: Drift-Aware Deadlines for Active Perceptioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation
  2. 2026World Models in Pieces: Structural Certification for General Agents
  3. 2026Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures
  4. 2026Boundary-State Control for Tool-Using Language-Model Agents: Commit-Time Consistency under State Drift
  5. 2026Governed Persistent Memory: Source-Bound State Semantics and Fail-Closed Release for Long-Horizon Agents
  6. 2026Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay
  7. 2026When Memory Updates but Behavior Does Not: Repairing Implicit Stale Dependencies in Personalized Agent Responses
  8. 2026The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissociates Commitment Drift from Binding Drift in Long-Horizon Agents