Detecting an Effect Is Not Learning to Act on It: A Reward-SNR Floor for LLM Acquisition Agents

• URL: http://arxiv.org/abs/2608.10441v1
• Date: Tue, 11 Aug 2026 03:46:23 GMT
• Title: Detecting an Effect Is Not Learning to Act on It: A Reward-SNR Floor for LLM Acquisition Agents
• Abstract summary: Pipelines can pay a per-example cost to acquire an auxiliary, model-derived observation, and then must decide when the acquired signal is worth using.<n>Our thesis is a distinction that is easy to miss: detecting that such a signal helps on average is not the same as learning to act on it per instance.<n>We explain this with one distinction, detecting a mean effect vs. learning a per-instance acquisition policy, and a reward-SNR detectability floor.
• Score: 1.5116447879757695
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. Our thesis is a distinction that is easy to miss: detecting that such a signal helps on average is not the same as learning to act on it per instance, and a reward-SNR floor governs when the second is even possible. Even when the signal is faithful and an in-sample oracle picking the top-b examples by realized reward shows a sizable apparent gain, no deployable policy can learn when to acquire it: across per-impression, cluster, regime, and uplift-tree granularities, learned routing never beats random, and a matched-moment noise placebo reproduces >=100% of the oracle's apparent gain -- the apparent "learnable structure" is order statistics of noise. We explain this with one distinction, detecting a mean effect vs. learning a per-instance acquisition policy, and a reward-SNR detectability floor: routing is estimable offline only if the reward SNR rho clears rho*(N) ~= 2.8/sqrt(N), with a positive control confirming a true low-SNR limit rather than a broken pipeline. As a concrete instantiation we introduce Structured Hypothesis Embeddings (SHE): a frozen LLM turns a user history into ranked, confidence-scored, evidence-grounded intent hypotheses, fused into a recommender. On three public datasets (MIND, REES46, Amazon-Beauty), SHE is faithful and calibratable, yet its value is backbone- and regime-conditional (significant over an ordered GRU, +0.0114, 95% CI [+0.0030, +0.0209], but a global redundancy gap indistinguishable from zero), and learned acquisition collapses at every granularity because all three datasets sit below the floor. The realizable unit is a design-time regime gate, not a per-instance policy. We release code and a one-command reproduction.

Related papers

• Retrieval-Guided Fine-Tuning as Noisy Estimation: Risk bounds and Architectural Analysis [1.381684956393831]
  Retrieval-Guided Fine-Tuning (RAG-FT) incorporates retrieved data directly into the training objective, but the statistical consequences of noisy retrieval during training remain theoretically undercharacterized.<n>We show that retrieval failure decays exponentially with task separation relative to noise, and derive explicit finite-sample conditions under which RAG-FT achieves lower risk than both target-only and full-corpus training.<n>We prove that the attention estimator's bias diverges as $(n2q)$ even under exact retrieval, while OLS risk remains $(d/n)$ for every noise
  arXiv  Detail & Related papers  (2026-09-13T12:51:02Z)
• Accurate Ensembles, Fragile Narratives: Multi-Scale Stacking and a Fidelity Audit of LLM-Generated Explanations for Credit Risk [0.0]
  Credit scoring increasingly relies on models whose decision logic cannot be read off their parameters.<n>A common proposal closes that gap with a language model: compute feature attributions, hand them to an LLM, and let it write the rationale.<n>We build such a system end to end and test whether the second half of the promise holds.
  arXiv  Detail & Related papers  (2026-08-08T13:22:14Z)
• When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion [0.0]
  Reinforcement learning with verifiable rewards (RLVR) can improve one-sample accuracy while making a model worse under repeated sampling.<n>We study this pass@k inversion: after training, the policy may solve fewer distinct problems than its base model at large $k$.<n>The failure concentrates on boundary prompts, where the base model contains rare correct trajectories that are recoverable by sampling but too sparse to reliably appear in finite RLVR rollout groups.
  arXiv  Detail & Related papers  (2026-07-12T17:17:18Z)
• Causal Label Recovery in Payment Networks [0.0]
  Fraud detection models in payment networks train on chargeback labels that are systematically biased.<n>A companion paper [arXiv05:26.27557] proved that these four impairments impose a minimax lower bound on detection performance.<n>We formalize the observation pipeline as a sequential missing-data problem with three stages and a corruption layer, and construct the Sequential Triply Robust estimator.
  arXiv  Detail & Related papers  (2026-05-28T02:43:34Z)
• Representation Without Reward: A JEPA Audit for LLM Fine-Tuning [1.2691047660244335]
  Joint-embedding predictive architectures (JEPAs) propose that a model should learn more useful abstractions when trained to predict latent representations rather than observed outputs.<n>For autoregressive language-model fine-tuning the principle entails a stricter requirement: the induced hidden-state geometry must reach the language-model head emphand improve the decoded task metric.<n>We test that requirement under a fixed Llama-3.2-1B-Instruct LoRA harness on natural-language-to-regex generation.
  arXiv  Detail & Related papers  (2026-05-14T20:27:32Z)
• Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization [74.91418266859297]
  Implicit process reward models (PRMs) provide fine-grained reward signals along the reasoning process.<n>PRMs suffer from a train-inference mismatch: training only constrains a sequence-level aggregate, whereas inference requires token-level scores to reflect local step quality.<n>We propose a novel Implicit Prefix-Value Reward Model (IPVRM), which directly learns a prefix-conditioned value function estimating the probability of eventual correctness.<n>We also propose Distribution-Level RL (DistRL), which computes TD advantages for both sampled tokens and high-probability candidate tokens.
  arXiv  Detail & Related papers  (2026-04-14T18:19:54Z)
• How Far Can Unsupervised RLVR Scale LLM Training? [57.44753418846446]
  Unsupervised reinforcement learning with verifiable rewards (URLVR) offers a pathway to scale LLM training beyond the supervision bottleneck.<n>Recent works leverage model intrinsic signals, showing promising early gains, yet their potential and limitations remain unclear.<n>We classify URLVR methods into intrinsic versus external based on reward sources, then establish a unified theoretical framework.
  arXiv  Detail & Related papers  (2026-03-09T17:38:11Z)
• Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior [58.751981587234916]
  This paper formalizes the Refinement Provenance Inference (RPI) audit task as Refinement Provenance Inference (RPI)<n>We propose RePro, a logit-based framework that fuses teacher-forced likelihood features with logit-ranking signals.<n>During training, RePro learns a transferable representation via shadow fine-tuning, and uses a lightweight linear head to infer provenance on unseen victims without training-data access.
  arXiv  Detail & Related papers  (2026-01-05T10:16:41Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision [26.922922043969958]
  We propose turning exploration into supervision through Compute as Teacher (CaT)<n>CaT synthesizes a single reference from a group of parallel rollouts and then optimizing toward it.<n>As a test-time procedure, CaT improves Gemma 3 4B, Qwen 3 4B, and Llama 3.1 8B.
  arXiv  Detail & Related papers  (2025-09-17T17:59:42Z)
• Learning to Reason without External Rewards [100.27210579418562]
  Training large language models (LLMs) for complex reasoning via Reinforcement Learning with Verifiable Rewards (RLVR) is effective but limited by reliance on costly, domain-specific supervision.<n>We explore Reinforcement Learning from Internal Feedback (RLIF), a framework that enables LLMs to learn from intrinsic signals without external rewards or labeled data.<n>We propose Intuitor, an RLIF method that uses a model's own confidence, termed self-certainty, as its sole reward signal.
  arXiv  Detail & Related papers  (2025-05-26T07:01:06Z)
• Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels [56.81761908354718]
  We propose a novel theoretically guaranteed clean sample selection framework for learning with noisy labels. Knockoffs-SPR can be regarded as a sample selection module for a standard supervised training pipeline. We further combine it with a semi-supervised algorithm to exploit the support of noisy data as unlabeled data.
  arXiv  Detail & Related papers  (2023-01-02T07:13:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.