arXiv AI
Jul 21
Teach it to stop, not just to click
arXiv:2607. 17136v1 Announce Type: cross Abstract: Agentic computer-use RL is reported in single runs, and those numbers mislead.
Sampling Luck Masquerades as Allocation Gain: Auditing Test-Time Budget Allocation for Neural Combinatorial Optimization
arXiv:2608. 13087v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) solvers report the best of many sampled solutions per instance, and the sample count is, by convention, identical for every instance.
Related stories
arXiv AI
Aug 11
When Is Benchmark Contamination Detectable? Information Limits and Power-Calibrated Audits
arXiv:2608. 07914v1 Announce Type: new Abstract: Behavioral contamination detectors can return "no evidence" either because a benchmark is clean or because the audit has little power.
arXiv Machine Learning
Jul 30
Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR
arXiv:2607. 26253v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by rollout generation, yet many sampled prompts produce saturated groups (all responses correct or all incorrect) whose zero reward variance yields no policy-gradient signal.
arXiv Machine Learning
Jul 14
When the Reward Suite Is Leaky: A Preregistered Causal Contrast of Natural Verifier False Positives in RLVR
arXiv:2607. 11022v1 Announce Type: new Abstract: The test suites used as RLVR rewards for code have natural false positives: per-task, persistent, asymmetric errors that accept the same wrong programs every time they appear, unlike the symmetric or resampled noise assumed by existing noise-robustness analyses.
arXiv Machine Learning
Aug 3
ALIVE: Warnings Before Exclusion in Budgeted Multi-Source Learning
arXiv:2607. 29400v1 Announce Type: new Abstract: A routing decision can be revised at the next transaction, but a latched source exclusion persists across later decisions.
arXiv AI
Jun 19
Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning
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.
arXiv Machine Learning
Aug 12
Detecting an Effect Is Not Learning to Act on It: A Reward-SNR Floor for LLM Acquisition Agents
arXiv:2608. 10441v1 Announce Type: new Abstract: Many pipelines can pay a per-example cost to acquire an auxiliary, model-derived observation -- an LLM's structured reasoning, a slow oracle, an expensive measurement -- and then must decide when the acquired signal is worth using.
arXiv Machine Learning
Aug 11
Quality-Diversity Stress Tests for Process Reward Models:What Archive Coverage Can and Cannot Certify
arXiv:2608. 08008v1 Announce Type: new Abstract: Process reward models (PRMs) score intermediate reasoning steps and are widely used for search, ranking, and training, but optimization can exploit these learned proxies by increasing reward while turning correct reasoning into incorrect reasoning.
arXiv Machine Learning
Aug 11
When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes
arXiv:2608. 07911v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have outgrown accelerator memory, and offloading expert weights to host memory is now standard.
arXiv AI
Jun 29
When Is an LLM Worth It for Hyperparameter Optimization? A Budget-Matched Study on Tabular Data Finds the Warm-Start Is a Default Configuration, Not the Model
arXiv:2606. 21641v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have been proposed as hyperparameter-optimization (HPO) advisors that "warm-start" search from prior knowledge, proposing strong configurations in very few evaluations.
arXiv AI
Jul 22
SFGA: A Statistics-First Gating Architecture with Adjudicative Escalation for Trustworthy SFT Data Procurement
arXiv:2607. 18960v1 Announce Type: cross Abstract: Procuring supervised fine-tuning (SFT) data forces a buyer to decide, before any downstream training, whether a candidate corpus is worth acquiring.
arXiv AI
Jul 22
Distribution-First Population Simulation: Collapse, Calibration, and Recall in Non-WEIRD LLM Persona Modeling
arXiv:2607. 18310v1 Announce Type: cross Abstract: Synthetic-population tools increasingly run every individual as an independent large language model (LLM) agent.