Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation

• URL: http://arxiv.org/abs/2609.10954v1
• Date: Thu, 10 Sep 2026 01:22:57 GMT
• Title: Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation
• Abstract summary: We introduce the fork ledger, which branches a deployment stream at pre-registered decision points into matched update and hold continuations under common random numbers.<n>It evaluates both continuations on the same episodes and records $R = R_mathrmupdate - R_mathrmhold$.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Continual world models must decide whether new data justify changing the model. Fixed replay schedules and prediction-error triggers specify when to update, but neither reveals the value of an individual update: one deployment run cannot show how the same model would have performed at that moment had it held its parameters. We introduce the fork ledger, which branches a deployment stream at pre-registered decision points into matched update and hold continuations under common random numbers. It evaluates both continuations on the same episodes and records $ΔR = R_{\mathrm{update}} - R_{\mathrm{hold}}$. Always applying one fixed update mechanism lowers return on all three simulated control tasks: CartPole ($-144.0$; checkpoint-bootstrap $95\%$ CI $[-185.4,-116.1]$, against a converged return near $650$), Walker ($-82.8$; $[-101.1,-61.7]$) and Cheetah ($-18.6$; $[-29.0,-6.6]$). Divergence is an outcome of applying the update, so the estimand counts every attempted fork; restricted to the $693$ of $720$ that did not collapse, CartPole and Walker are unchanged in sign ($-113.4$ and $-82.1$) and Cheetah becomes unresolved ($-3.9$; $[-17.5,+13.0]$). The task is the unit of inference: each contributes $240$ attempted forks over five pretrained checkpoints crossed with two drift directions. The ledger makes counterfactual utility observable for a fixed mechanism, allowing triggers to be judged by the updates they select rather than by surprise detection alone.

Related papers

• ActionSplice: In-Flight Action Editing for Interactive World Models [4.400011068855375]
  Chunk-autoregressive video world models typically condition each generated chunk on one action.<n>We introduce Actionplice, an inference framework that formulates this problem as Counterfactual State Transport (CST)<n>A temporal-splicing variant $mathrmCST*R$ preserves a temporal prefix and updates only the suffix.<n>$mathrmCST*T$ reduces suffix LPIPS by 56.1% and 77.5%, respectively, while providing $2.73times$ and $1.69times$ pixel-ready speedups over waiting.
  arXiv  Detail & Related papers  (2026-09-08T04:21:36Z)
• Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors [51.56484100374058]
  Autoregressive models accumulate error over long rollouts, yet at deployment there is no ground truth to measure it against.<n>We train a single conditional latent diffusion model that steps a dynamical system forward or backward in time via a direction flag.<n>We show that this bidirectionality supplies a measurement-free test-time error signal.
  arXiv  Detail & Related papers  (2026-08-01T13:49:46Z)
• Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks [10.839956062772792]
  Three agent-safety benchmarks rank the same 18 models differently.<n>R-Judge specificity against AgentHarm safety correlates $-0.64$ at $n=7$ and $+0.02$ at $n=18$, and a quarter of random size-7 subsets reach $|| geq 0.5$ around that near-zero value.<n>AgentHarm shows the strongest held-out association, $=+0.72$ with three-template jailbreak safety after controlling capability.
  arXiv  Detail & Related papers  (2026-07-30T03:45:10Z)
• Teach it to stop, not just to click [0.0]
  We show a repaired policy's success rate is dominated by upstream footing.<n>We release a library (cua_reliability) for routine k-seed reporting.
  arXiv  Detail & Related papers  (2026-07-19T08:46:06Z)
• A Fast Gaussian Mechanism under Continual Observation, with Applications [10.345196226375455]
  We consider the problem of privately releasing a $k$-dimensional vector under updates.<n>We release an approximation of $A(1),dots,A(T)$ with additive noise of magnitude $textpolylog(T)$.<n>We present two data management applications, of independent interest, that use our technique in conjunction with differentially private CountSketches.
  arXiv  Detail & Related papers  (2026-06-10T07:36:58Z)
• The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations [50.43168858368539]
  Large language models confidently produce outdated answers, and no existing method can detect them.<n>We show this is not an engineering failure but a structural one: temporal drift is encoded as a direction in the residual stream geometrically to both correctness and uncertainty.
  arXiv  Detail & Related papers  (2026-05-09T22:27:31Z)
• Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production [55.76222360698305]
  We explore a class of supervised training objectives that allow a language model to dynamically and autonomously scale the number of compute steps used for each input token.<n>For any token, the model can request additional compute steps by emitting a don't know> output.<n>We find that the CYB model requests additional steps when doing so improves accuracy, and the model adapts its processing time to token-level complexity and context.
  arXiv  Detail & Related papers  (2025-10-13T21:07:05Z)
• From Continual Learning to SGD and Back: Better Rates for Continual Linear Models [50.11453013647086]
  We analyze the forgetting, i.e., loss on previously seen tasks, after $k$ iterations.<n>We develop novel last-iterate upper bounds in the realizable least squares setup.<n>We prove for the first time that randomization alone, with no task repetition, can prevent catastrophic in sufficiently long task sequences.
  arXiv  Detail & Related papers  (2025-04-06T18:39:45Z)
• Variance-Dependent Regret Lower Bounds for Contextual Bandits [65.93854043353328]
  Variance-dependent regret bounds for linear contextual bandits, which improve upon the classical $tildeO(dsqrtK)$ regret bound to $tildeO(dsqrtsum_k=1Ksigma_k2)$.
  arXiv  Detail & Related papers  (2025-03-15T07:09:36Z)
• Near-Optimal Regret Bounds for Multi-batch Reinforcement Learning [54.806166861456035]
  We study the episodic reinforcement learning (RL) problem modeled by finite-horizon Markov Decision Processes (MDPs) with constraint on the number of batches. We design a computational efficient algorithm to achieve near-optimal regret of $tildeO(sqrtSAH3Kln (1/delta))$tildeO(cdot) hides logarithmic terms of $(S,A,H,K)$ in $K$ episodes. Our technical contribution are two-fold: 1) a near-optimal design scheme to explore
  arXiv  Detail & Related papers  (2022-10-15T09:22:22Z)
• Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning [77.22019100456595]
  We show a training algorithm for distributed computation workers with varying communication frequency. In this work, we obtain a tighter convergence rate of $mathcalO!!!(sigma2-2_avg!! . We also show that the heterogeneity term in rate is affected by the average delay within each worker.
  arXiv  Detail & Related papers  (2022-06-16T17:10:57Z)
• Minimal Expected Regret in Linear Quadratic Control [79.81807680370677]
  We devise an online learning algorithm and provide guarantees on its expected regret. This regret at time $T$ is upper bounded (i) by $widetildeO((d_u+d_x)sqrtd_xT)$ when $A$ and $B$ are unknown.
  arXiv  Detail & Related papers  (2021-09-29T14:07:21Z)

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.