The paper presents a certified rule that determines whether unseen data should be incorporated into a pretrained model’s context or its weights, based on an exact law for their information value. This law quantifies the code length saved on held‑out queries as the expected bits stored about the query, adjusted by a prior repair and decoding loss, and applies to any model, architecture, dataset, or task. The authors demonstrate that the rule’s ceilings correctly certify choices across diverse models—including transformers, TabPFN, occupancy networks, and stereo networks—and that an anytime‑valid test can reliably select the better approach (e.g., TabPFN over XGBoost or GPT‑2’s cache over fine‑tuning) with controlled error rates.
arXiv:2608.21098v1 Announce Type: new Abstract: Fusing prior knowledge with data-driven learning is attractive where data is scarce, yet no controlled account says when it helps, is redundant, or har...
arXiv:2609.36426v1 Announce Type: cross Abstract: A detector pretrained on a broad corpus is fine-tuned on a narrow domain, its in-domain accuracy improves, and it ships. We ask what happens meanwhil...
arXiv:2608. 12652v1 Announce Type: cross Abstract: Benchmark contamination is diagnosed today with n-gram overlap, with likelihood-based membership inference, or with canary strings, and each needs something usually unavailable: the training corpus, a well-chosen test statistic, or foresight at dataset release.
The paper investigates when an in‑context learner should expand its hypothesis space, framing the decision as a costly sequential problem where prediction failures must be translated into structural evidence and then into an action. Using a Structural Revision Environment that allows exact Bayesian analysis, the authors find that the optimal decision to expand is governed by a value boundary rather than a simple evidence threshold, and that this boundary depends on the price of expansion, the remaining horizon, and the specific predictions that cannot be repaired locally. Experiments with transformers and language models show that while these models exhibit a failure‑sensitive signal, they often fail to incorporate cost and horizon considerations into their expansion decisions, and post‑training adjustments to priors or prediction sharpness do not alter the expansion criterion.
arXiv:2609.01244v1 Announce Type: new Abstract: Every supervised fine-tuning run forces the same chain of decisions, such as learning rate, batch size, LoRA or full fine-tuning, how many epochs, whic...
The paper investigates how conversational Retrieval-Augmented Generation (RAG) benchmarks that rely on relevance judgments to determine context sufficiency can be misleading. By re‑running official baselines on the RETECO track and evaluating with both large‑language‑model judges and a blind audit, the authors show that stronger retrievers produce a higher proportion of contexts lacking gold documents yet still containing the answer, leading to a sharp drop in shortcut precision from 0.68 to 0.10. The study demonstrates that many false misses arise from hard negatives, gold content from other turns, or neighboring chunks, and that using retrieval scores alone as a sufficiency detector can underestimate answerability by up to 0.19 in AUROC.
The paper introduces LRE (Learned Relevance Eviction), a lightweight, CPU‑only, language‑model‑free scorer that learns which parts of an agent’s interaction history are task‑critical and preserves them verbatim. In experiments, LRE matches or surpasses baseline eviction policies on accuracy‑cost trade‑offs, recovers 93% of full‑history accuracy, reduces worst‑case prompt size by 52%, and outperforms dense and token‑pruning encoders in conversational memory while being 295–1569× smaller. The method also achieves superior budgeted answer quality on LoCoMo reading and can be trained annotation‑free, recovering 95% of supervised scorer performance.
arXiv:2607. 21692v2 Announce Type: replace Abstract: Sparse attention prunes a long context to the blocks a model needs, and the usual selector is distilled from a dense teacher's attention.
arXiv:2606. 27472v1 Announce Type: cross Abstract: Large language model (LLM) agents operate over long, multi-session interactions in which facts change: a user moves, a price updates, a plan is revised.
SkillGate is a method that trains agents to select the correct skill from a large slate during an episode by separating credit signals for skill selection and execution. It addresses the problem of selector credit starvation, where traditional outcome-rewarded RL fails to give sufficient credit to the skill-naming tokens, especially in long-horizon tasks. Experiments on five benchmarks show that SkillGate improves a 9B policy’s success rate from 40.8% to 53.2%, reduces exposure to misleading candidates, and requires fewer skill reads.
arXiv:2606. 31208v1 Announce Type: new Abstract: Large tabular models (LTMs), i.
arXiv:2610.15218v1 Announce Type: new Abstract: A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the...