The paper investigates how to handle a large‑language‑model’s weak verifier that accepts a response, followed by a second call that may resample or reroute. It introduces three decision gates—recoverable stopping debt, two‑sided FIT action support, and held‑out value from an outcome‑blind selector—to determine action selection, which is treated as an identification problem. Experiments on MBPP+, LiveCodeBench, and BigCodeBench show that while stopping debt exists, the current evidence does not identify when to resample versus reroute.
arXiv:2606. 31511v1 Announce Type: cross Abstract: In deployment settings where retraining is infeasible, small frozen code models are routinely asked to repair a failed program after seeing their own failing output, usually treated as a retry mechanism.
arXiv:2609.25052v1 Announce Type: new Abstract: "An agent that writes its conclusions into a store it later retrieves from closes a loop usually reported as one-way contamination. Taking the loop to...
arXiv:2608. 12599v1 Announce Type: new Abstract: Multi-turn dialogues let users revoke constraints as easily as impose them, but revocation does not reliably take effect: models keep enacting withdrawn requirements (occasionally beneath comments asserting their removal), a failure we call \emph{behavioral relapse}, or revocation inertia.
arXiv:2606. 05633v1 Announce Type: new Abstract: Retrieval-augmented QA pipelines often route retrieved passages through an LLM \emph{rewriter} before a smaller reader, lifting F1 by tens of points on multi-hop benchmarks; this gain is typically credited to improved evidence quality.
arXiv:2607. 26117v1 Announce Type: cross Abstract: Self-repair - returning a failed program to the model together with its test output and asking for a correction - is a standard component of code agents, and is almost always evaluated against a baseline that does not retry at all.
arXiv:2608. 03222v1 Announce Type: cross Abstract: Software engineering (SWE) agents resolve repository-level issues through long trajectories that grow increasingly expensive as context accumulates.
arXiv:2607. 18553v1 Announce Type: cross Abstract: Can a language model read the quality of ongoing computation, and can an external intervention turn that readout into better outcomes?
arXiv:2607. 19442v1 Announce Type: cross Abstract: Machine unlearning is commonly evaluated by matching a retrained oracle on trained probes.
arXiv:2608. 09254v1 Announce Type: new Abstract: LLM analytics agents are evaluated on SQL syntax accuracy, but production failures look different: questions with two valid business definitions, questions the warehouse cannot answer, deprecated columns after a schema change, and queries that execute successfully while returning the wrong business number.
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:2608. 07813v1 Announce Type: new Abstract: An LLM judge deployed inside a reasoning pipeline does not merely measure quality, it decides which answer ships.
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.