Stateful CARS: Exact Cross-History Reuse for Policy-Constrained LLM Agents

• URL: http://arxiv.org/abs/2608.08282v1
• Date: Sat, 08 Aug 2026 18:26:25 GMT
• Title: Stateful CARS: Exact Cross-History Reuse for Policy-Constrained LLM Agents
• Abstract summary: We study exact sampling from the model distribution conditioned on a hard stateful validator.<n>Stateful CARS freezes a bank of sound state--continuation schemas within each attempt.<n>Cross-history transfer helps only in an internal matched-key ablation.
• Score: 0.9558392439655014
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tool-using language-model agents face constraints whose meaning changes with observations and prior actions. We study exact sampling from the model distribution conditioned on a hard stateful validator while reusing invalidity certificates across histories. Stateful CARS freezes a bank of sound state--continuation schemas within each attempt and removes every trajectory containing a certified continuation at a matching abstract state. An exact residual Doob transform samples from the resulting proposal. We give a checkable future-validity bisimulation condition, prove schema soundness, adaptive exactness, i.i.d.\ outputs, almost-sure termination, monotone acceptance, and compression invariance, and characterize computation by the number of reachable full-history product states. This number can be exponential for a history-dependent language model; the evaluated method therefore makes no generic finite-trie scalability claim. On enumerable workflows, its analytic law matches the valid conditional to $10^{-16}$ at validity probability $6\times10^{-8}$, whereas state-aware local decoding can be $0.97$ away. A matched comparison is negative: observation-keyed official CARS is cheaper in sampler steps (root/Stateful ratio $0.942$ $[0.934,0.951]$), and the Qwen comparison is null ($0.99$ $[0.90,1.08]$). Cross-history transfer helps only in an internal matched-key ablation ($1.27\times$). Thus the evidence supports exact schema-induced conditioning, not a systems advantage over CARS.

Related papers

• Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States [4.505185728893222]
  We propose a reference-based method that audits bias in hidden-state representations across related model variants.<n>Because fine-tuning reshapes representation geometry, absolute hidden states are not directly comparable.<n>We measure how target groups shift in their association with positive and negative attributes.
  arXiv  Detail & Related papers  (2026-09-09T11:33:35Z)
• Probabilistic Model Checking of Autoregressive Neural Sequence Models [4.570003973862485]
  Test-set accuracy is silent on two issues that matter when deploying autoregressive neural sequence models.<n>How much probability mass the system under test places on constraint-violating alternatives that are reachable under sampling.<n>We answer both with probabilistic model checking.
  arXiv  Detail & Related papers  (2026-09-01T07:37:55Z)
• Drift Variation Autoencoder: Unifying Generation and Representation Learning through Conditional Posterior Flow Matching [0.0]
  This work takes the corresponding posterior $P(Xmid C)$ as the common statistical object for conditional generation.<n> Drift Variation autoencoder trains a masked encoder $Z=E(C)$ and a conditional flow decoder with one clean-prediction Flow Matching loss.
  arXiv  Detail & Related papers  (2026-08-25T20:38:50Z)
• SANE: State Anomaly Neutralization for Stable Extreme-Context Delta-Rule Models [53.86918766240095]
  Delta-Rule recurrent models maintain a fixed-size state, enabling $O(1)$ inference memory but potentially becoming unstable under extreme-context extrapolation.<n>We propose textbfState Anomaly Neutralization (SANE), which applies adaptive $tanh$ compression at chunk boundaries while preserving the intra-chunk parallel structure.
  arXiv  Detail & Related papers  (2026-08-23T10:41:07Z)
• From Approachability Residuals to Anytime-Valid Evidence: The Online Convex Geometry of Testing by Betting [0.1624454100511275]
  Gambling-based sequential tests and Blackwell approachability are linked by a rate-explicit reduction through support-functions.<n>We prove the exact pathwise identity $$ dist(bar r_T,S) =frac1Tsum_t=1Tq_t+fracReg_TT.
  arXiv  Detail & Related papers  (2026-08-10T11:23:30Z)
• Calibrated e-CUSUM Decoding for Quantized Reasoning Models: Why Token Log-Probability Is the Wrong Observable for Decoding Monitors [0.6999740786886536]
  Low-bit quantization makes small reasoning models inexpensive to deploy but can degrade their chains of thought.<n>We show that the centered token log-probability increment $log p(w_t)+H_t$ is the wrong observable for this purpose.<n>We introduce a training-free decoding controller that combines a degeneration-aware alarm score fusing token uncertainty with explicit repetition.
  arXiv  Detail & Related papers  (2026-07-13T09:34:36Z)
• Certified Finite-Shot Operating Windows for Virtual Distillation and Symmetry Verification [0.0]
  We develop a finite-shot operating-window theory that makes comparison certifiable for virtual distillation (VD) and symmetry verification (SV)<n>For VD, the law captures the statistical bias and denominator instability of its quotient estimator, with a concentration certificate locating the sample size beyond which the quotient is trustworthy.<n>For SV, it isolates the bias floor left by undetectable errors and the sampling penalty set by the acceptance probability.
  arXiv  Detail & Related papers  (2026-06-13T20:42:40Z)
• Scaling Laws for Agent Harnesses via Effective Feedback Compute [53.68149869349268]
  emphEffective Feedback Compute (EFC) is a trace-level scaling coordinate that credits feedback only when it is informative, valid, non-redundant, and retained for subsequent decisions.<n>EFC-based coordinates consistently predict failure rates better than raw-compute baselines.
  arXiv  Detail & Related papers  (2026-05-28T09:45:47Z)
• When Are Trade-Off Functions Testable from Finite Samples? [4.706977254727891]
  We study finite-sample inference for the trade-off function of two unknown probability distributions.<n>By inverting the test, we also obtain simultaneous confidence bands for the whole trade-off curve.
  arXiv  Detail & Related papers  (2026-05-11T16:07:48Z)
• 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)
• Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols [51.56484100374058]
  We propose a paired-outcome measurement interface for auditing a single protocol step on exact-match tasks.<n>For each instance, the interface records a baseline correctness bit and a post-step correctness bit.<n>These rates predict accuracy changes and define a reusable empirical interface testable across seeds, mixtures, and pipelines.
  arXiv  Detail & Related papers  (2026-04-20T13:25:40Z)
• See Less, Drive Better: Generalizable End-to-End Autonomous Driving via Foundation Models Stochastic Patch Selection [51.59559387222532]
  Recent advances in end-to-end autonomous driving show that policies trained on patch-aligned features generalize better to Out-of-Distribution (OOD)<n>We present $2.4-Patch-Selection (SPS), a simple yet effective approach for learning policies that are more robust, generalizable, and efficient.
  arXiv  Detail & Related papers  (2026-01-15T18:58:33Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• Certifiably Robust Model Evaluation in Federated Learning under Meta-Distributional Shifts [8.700087812420687]
  We provide guarantees for the model's performance on a different, unseen network "B"<n>We show how the principled vanilla DKW bound enables certification of the model's true performance on unseen clients within the same (source) network.
  arXiv  Detail & Related papers  (2024-10-26T18:45:15Z)
• Generalized Differentiable RANSAC [95.95627475224231]
  $nabla$-RANSAC is a differentiable RANSAC that allows learning the entire randomized robust estimation pipeline. $nabla$-RANSAC is superior to the state-of-the-art in terms of accuracy while running at a similar speed to its less accurate alternatives.
  arXiv  Detail & Related papers  (2022-12-26T15:13:13Z)

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.