To the authors' knowledge, AdmitOR is the first label-free admission mechanism designed around an explicitly calibrated false-discovery target, and the transfer failure identifies a necessary condition for extending it to wild streams.
Abstract
Experience-learning agents for optimization modeling improve by storing verified skills, but existing learners admit knowledge by checking against known answers, which real ticket streams do not provide. The natural label-free alternatives are unreliable: on a 300-problem label-blind stream, admitting every executable model poisons roughly one admission in four, while single-instance agreement accepts models that match at one value but differ elsewhere. We propose AdmitOR, an admission gate built on calibrated external behavioral evidence. Candidates from three model families, prompting strategies, and solver stacks are run on instances resampled from an extracted parameter domain; agreement across the resulting value-function traces is summarized by a cross-family clique, and a calibrated threshold returns accept, abstain, or escalate. The preregistered false-discovery criterion holds on calibration data but not on the wild stream. We report this negative result in full and trace most failures to benchmark texts that do not faithfully encode their labeled instances. Comparing four admission judges on one collection of logs inside a state-of-the-art skill learner, AdmitOR raises admission precision to 0.927, against 0.871 for majority vote and 0.726 for execution success, yielding 3.1x and 8.0x fewer poisoned admissions. Its library is the smallest and attains the highest macro accuracy across five public benchmarks, 58.4 against 54.8 for majority vote and 53.9 for the ground-truth-labeled library. The 3.5-point gain over majority vote is supported by a paired bootstrap and survives correction for a host-side anomaly. To our knowledge, AdmitOR is the first label-free admission mechanism designed around an explicitly calibrated false-discovery target. The transfer failure identifies a necessary condition for extending it to wild streams.
This work defines a resource-indexed challenge-power modulus that characterizes the largest gap compatible with passage, and proves the converse frontier: without coverage, a first-order ReLU trainer can reach infinitely many exact conditional head optima while converging to a non-global point.
Farhang Yeganegi, Arian Eamaz, M. Soltanalian· 0 citations
Improving a language model today means retraining it: enormous compute, a new opaque model each cycle, non-deterministic output. We take the opposite path: the model stays frozen, and a persistent memory of verified solutions grows beside it. Once a problem family is solved and has passed an independent verification step that never consults the answer key, every new instance of that family is answered at zero generation tokens, bit-exact, deterministically. Across 180 fresh instances spanning nine problem families, four architectures from four vendors - dense and mixture-of-experts - each score 180/180 at zero generation tokens per answer: execution-bound capability decoupled from parameter scaling. A negative control attributes the capability fully to the memory: emptied, it solves nothing. The same verify-before-store contract holds for open-ended reasoning: 88/88 consistency-gated acceptances across all four models, machine-checked formal proof, and reasoning-method transfer at 77/80. Memory selection takes 1.4 microseconds; a full reuse completes in 6-23 ms at 36 mWh. Approximate similarity retrieval selects the wrong item 94.3% of the time on a 4,500-item verified store where exact addressing makes zero errors. The store also serves as working context at a scale no shipped engine matches: a 6,000,000-token movable window on a single 46 GB GPU at flat memory, where vLLM stops at 30,399 tokens and SGLang silently truncates past 32,000. On published benchmarks, frontier models remain far ahead of any 12B at raw from-scratch reasoning; on everything this system has solved and verified, the comparison inverts: a frontier API call pays a fresh generation pass on every query, forever, while verified reuse costs zero tokens and returns the identical bits every time. A public testbench with free, rate-limited access accompanies this report: https://corbenic-galahad-bench.hf.space
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. We formulate PRM stress testing as a quality-diversity search problem using MAP-Elites, retaining the most severe correctness-flipping edit in each behavior-space region while separating search coverage from exploit coverage. We characterize what such archives certify: finite-cell repair bounds covered-cell tail risk and average residual severity but cannot bound the worst remaining cell from covered fraction alone; under Lipschitz post-repair loss and metric-cover auditing, the residual is bounded by archive fitting error plus the Lipschitz constant times the covering radius. A controlled landscape validates this certificate and the impossibility of any fraction-only worst-case guarantee. On real PRMs, the search reveals an aggregation-dependent vulnerability in Qwen2.5-Math-PRM-7B: padding yields 44 strict exploits with maximum gain 0.294 under mean pooling versus one exploit under minimum readout; a matched syntactic control isolates the mechanism, and an RLHFlow value-head model shows the same qualitative effect with maximum gain 0.005. A predeclared paired LoRA repair protocol reduces exploit rates from 0.148 to 0.037 to 0.074, lowers the worst attack from 0.333 to 0.177 to 0.212, improves ranking AUROC without degrading best-of-4 accuracy, attributes gains to adversarial fine-tuning rather than archive diversity, and is confirmed by independent unpaired replications (44 to 1, clean-split worst gain 0.0092, MATH-500 41 to 0, clean ranking 40/40).
This work proposes AutoVerifier, a residual-guided non-parametric optimization method that learns biases from recurring verifier errors and promotes them to code modules or prompt guidance only after replay validation detects no direct regressions, keeping accepted updates auditable, editable, and reusable.
This framework yields a practical pre-deployment diagnostic: estimate the oracle gap, then measure coverage, signal fidelity, and harm before investing in collaboration.
The proposed TRACE-QA, a training-free multi-agent protocol that routes each instance to a sparse set of reasoning operators, constructs option-blind necessity constraints, audits every candidate in a structured elimination ledger, revisits risky eliminations through global risk-aware rescue, and aggregates role-specialized judge votes, supports constraint-guided elimination as an auditable alternative to answer-first debate.
Jiaxin Lu, Hao Chen, Yan-Cheng Zhu et al.· Journal of King Saud Univers...· 0 citations
