arXiv:2610. 00256v1 Announce Type: new Abstract: External verification can correct individual outputs while leaving a self-reinforcing population in the basin of a wrong consensus.
arXiv:2606. 19808v1 Announce Type: new Abstract: Test-time reasoning is increasingly used as a serving-time control knob, but extra reasoning is not uniformly valuable: it can repair failed attempts, waste compute on already-correct answers, or introduce harmful answer changes.
The paper investigates whether self-consensus—stopping a reasoning model when its partial trajectory’s answers agree—can safely reduce inference cost. A large sweep of 3,520 consensus rules on two models and three benchmarks failed to meet predefined safety criteria, while a boundary‑confidence control (DEER) succeeded. The study shows that agreement signals that an answer persists under a fixed probing procedure, not that reasoning has finished, leading to premature stops and missed corrections even when token savings are significant.
arXiv:2606. 15621v1 Announce Type: new Abstract: Per-token counterfactual credit estimation asks which token in a language-model rollout caused the final answer to be right or wrong: cut the transcript at a pivot, substitute an alternative token, replay continuations, and compare outcomes.
arXiv:2609. 10954v1 Announce Type: new Abstract: Continual world models must decide whether new data justify changing the model.
arXiv:2608. 10145v1 Announce Type: new Abstract: LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached on TwoRoom, its simplest diagnostic environment.
arXiv:2609.13714v1 Announce Type: new Abstract: An updated model can improve an aggregate metric while degrading a slice that matters to a downstream user. We study checkpoint selection subject to no...
arXiv:2604. 18245v3 Announce Type: replace Abstract: Large language models operate in protocols containing multiple calls, yet added calls are usually evaluated only by their net effect.
The paper investigates whether large language models’ reasoning traces truly contain early, informative signals or merely reflect budget and difficulty confounds. Using a restart‑controlled truncation probe, the authors compare continuation success rates against from‑scratch restart curves across 178 problem‑model pairs, finding that only one case shows prefix‑limited success and that continuing a model’s own prefix generally outperforms restarting. A difficulty‑controlled test and two generation‑free analyses reveal that early internal signals do not carry outcome information beyond a problem‑difficulty baseline, underscoring the need for proper counterfactual controls.
arXiv:2606. 00329v1 Announce Type: cross Abstract: Recursive systems can enter collapse-like regimes -- self-reinforcing amplification, persistent recursion, and narrowing diversity that mask accelerating internal degradation -- before overt failure becomes visible.
The paper investigates the safety of Code World Models, where a language model generates executable world models that a planner uses. It shows that accepting a model based on sampled transitions only guarantees sample consistency, not full safety, because the probability of missing critical events decays as (1‑r)^N. Experiments on hybrid instruments reveal that omitted mode‑boundaries can severely limit planner performance, and that even sophisticated LLMs (GPT‑5.x) struggle to repair such omissions in higher‑dimensional settings.
arXiv:2609. 29140v1 Announce Type: new Abstract: Repeated evaluation can estimate a benchmark score accurately while still requiring replication to certify narrow uncertainty.
The paper investigates the safety of Code World Models, where a language model generates an executable world model that a planner uses, and the model is accepted if it reproduces sampled transitions. It defines the pipeline’s danger as the expected risk, showing that the probability of missing a critical event across N independent rollouts is (1‑r)^N, and that an additional acceptance sample adds to the exponent. Experiments on hybrid instruments reveal that mode‑blind models can be exploited, and the authors provide theoretical bounds on localization budgets and demonstrate that acceptance only guarantees sample consistency, covering about two percent of the planner’s queries.