arXiv Machine Learning

Decodable In-Context State and Model Output Across Training

The paper investigates how a probe can decode in‑context bindings on model errors and how probe‑guided steering can repair them. It tracks probe accuracy, model output, and steering response across public pretraining and post‑training checkpoints, noting that probe accuracy improves during Pythia pretraining and that steering benefits grow with model size. The study also shows that decoders trained on final state or candidate logits do not outperform each other on late‑checkpoint errors, and presents an information‑theoretic counterexample explaining why decodability on errors alone cannot prove discarded output information.

arXiv Machine Learning
Sep 11

Legible Failures: Detecting and Repairing In-Context Binding Errors

The paper investigates in-context binding errors in language models, showing that a linear probe can recover correct entity bindings from frozen hidden states even when the model outputs incorrect bindings. Across 16 checkpoints, the probe’s accuracy on failure cases surpasses a baseline by about 0.196, and a probe‑based score improves failure detection over the model’s confidence by 0.079 AUROC. Steering the residual stream toward the probe‑decoded binding further boosts accuracy by an average of 0.168 across eight models.

By Manas Venkata Sai Ravulapalli, Samrath Singh Chadha, Abhinav M. Hari
arXiv Machine Learning
Oct 28

Checkpoint Reload Explains Most of the Measured State Gap in Two State Discovery Reproductions

The paper investigates whether the latent states reconstructed during inference match those stored during training in temporal models, focusing on State Discovery in World Machine. By comparing stored state tables with rollouts from the best‑validation checkpoint and the last‑epoch weights, the authors find that reloading the checkpoint used to write the table eliminates 90–91% of the mean per‑dimension Wasserstein‑1 distance, explaining most of the observed state gap. Causal distillation and frozen SD updates fail to meet their criteria under either checkpoint.

By Weijia Han, Lisha Qu
arXiv Machine Learning
Sep 1

The Intervention Gap in Latent World Models

The paper introduces the concept of intervention fidelity in latent world models, measuring whether a model’s open‑loop transitions align with actual environment interventions. Experiments on TD‑MPC2, Cheetah, and DreamerV3 show that high reward fit does not guarantee fidelity, and that self‑supervised models can outperform task‑anchored ones in preserving intervention effects. The authors propose a capture‑gated audit to localize failures and argue that fidelity must be directly audited on the model’s native interface.

By Donna Vakalis
arXiv Machine Learning
Oct 3

Sharpen Before You Adapt: Data-Free Entry-State Sharpening for Test-Time Reinforcement Learning

The paper introduces entry-state sharpening, a data‑free pre‑training step that prepares a language model’s checkpoint in a sharper, lower‑entropy state before test‑time reinforcement learning (TTRL). By reducing policy entropy, the model can more efficiently use its limited adaptation budget, leading to higher endpoint conversion efficiency across tasks such as MATH, GPQA, and AMC. Experiments with different data‑free objectives (e.g., R‑Zero vs. SPIRAL) demonstrate that the choice of pre‑training objective strongly influences the checkpoint’s readiness for TTRL, and a label‑free self‑distillation intervention can further sharpen the entry state.

By Zhanming Zhang, Vinoth Selvendran
arXiv AI
Oct 9

Evaluating Exact Output and Checkpoint-State Prediction in Real Programs

The paper introduces a benchmark for predicting a program’s final output and checkpoint state using only its source code and input, extending CRUXEval-style tasks with both short‑ and long‑trace inputs and checkpoints inside and after loops. It evaluates 400 cases from 371 Python and C++ programs across seven settings from four model families, achieving up to 93.0% accuracy on short‑trace final output and 77.0% on long‑trace final output, with reasoning‑enabled settings outperforming non‑reasoning ones by 33.1 to 55.2 percentage points. The study also shows that longer‑trace inputs can change correctness outcomes and that the benchmark reveals errors that short‑output scores alone would miss.

By Xiaohong Chen, David Bucur, Chenglong Ma, Yi Zhang, Lingming Zhang, Sriram Vishwanath, Grigore Rosu
arXiv AI
Aug 24

Beyond End-to-End Success: Diagnosing Failures in Long-Horizon Security LLM Agents

The paper introduces a diagnostic framework for long‑horizon security LLM agents that uses checkpoints to distinguish failures occurring before and after a model’s capability is exposed, and applies controlled interventions to pinpoint upstream bottlenecks. The methodology is tested on four task families—delayed reuse of discovered information, reuse of observed state, recovery from failed strategies, and decision making after uncertain outcomes—revealing that many failures happen before the agent observes the state it later needs to reuse. Experiments with Gemini 2.5 Flash and Gemini 3.7 Flash show that targeted protocol‑disambiguation guidance can significantly alter state observation rates and that the primary source of failure can shift across model generations, underscoring the need for fine‑grained failure diagnostics rather than relying solely on overall task success.

By Wei Shao, Chongzhou Fang, Zuxiong Tan, Zequan Liang, Setareh Rafatirad, Avesta Sasan, Houman Homayoun