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

arXiv: https://arxiv.org/abs/2608.10441 · HTML: https://mlsanity.com/paper/2608.10441/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 31 of its 46 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)
- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 30 of 31)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Estimation and Inference of Heterogeneous Treatment Effects using Random Forests](https://mlsanity.com/paper/1510.04342/) (2015)
- [Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning](https://mlsanity.com/paper/1706.03461/) (2017)
- [Quasi-Oracle Estimation of Heterogeneous Treatment Effects](https://mlsanity.com/paper/1712.04912/) (2017)
- [Consistent Estimators for Learning to Defer to an Expert](https://mlsanity.com/paper/2006.01862/) (2020)
- [RouterBench: A Benchmark for Multi-LLM Routing System](https://mlsanity.com/paper/2403.12031/) (2024)
- [Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer](https://mlsanity.com/paper/1711.06664/) (2017)
- [LLMRec: Large Language Models with Graph Augmentation for Recommendation](https://mlsanity.com/paper/2311.00423/) (2023)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE](https://mlsanity.com/paper/1809.11142/) (2018)
- [A Unified Approach to Routing and Cascading for LLMs](https://mlsanity.com/paper/2410.10347/) (2024)
- [Towards Open-World Recommendation with Knowledge Augmentation from Large Language Models](https://mlsanity.com/paper/2306.10933/) (2023)
- [Learning to Route LLMs with Confidence Tokens](https://mlsanity.com/paper/2410.13284/) (2024)
- [BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute](https://mlsanity.com/paper/2506.22716/) (2025)
- [Active Feature Acquisition with Generative Surrogate Models](https://mlsanity.com/paper/2010.02433/) (2020)
- [LLMRouterBench: A Massive Benchmark and Unified Framework for LLM Routing](https://mlsanity.com/paper/2601.07206/) (2026)
- [Evaluating Treatment Prioritization Rules via Rank-Weighted Average Treatment Effects](https://mlsanity.com/paper/2111.07966/) (2021)
- [Causal Decision Making and Causal Effect Estimation Are Not the Same... and Why It Matters](https://mlsanity.com/paper/2104.04103/) (2021)
- [RAGEN-2: Reasoning Collapse in Agentic RL](https://mlsanity.com/paper/2604.06268/) (2026)
- [A Survey on Active Feature Acquisition Strategies](https://mlsanity.com/paper/2502.11067/) (2025)
- [Experimental Evaluation of Individualized Treatment Rules](https://mlsanity.com/paper/1905.05389/) (2019)
- [Beating the Winner's Curse via Inference-Aware Policy Optimization](https://mlsanity.com/paper/2510.18161/) (2025)
- [LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers](https://mlsanity.com/paper/2608.06867/) (2026)
- [Opportunity Is Not Realizability: Selection-Valid Diagnostics for Multi-LLM Routing](https://mlsanity.com/paper/2608.08265/) (2026)
- [Winner's Curse Drives False Promises in Data-Driven Decisions: A Case Study in Refugee Matching](https://mlsanity.com/paper/2602.08892/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly used as costly, on-demand components in real systems, but calling them indiscriminately can waste substantial compute, latency, and serving budget. The key deployment question is therefore not only whether an LLM helps on average, but when it is worth calling. We identify a common failure mode, which we call acquisition collapse: an LLM signal can appear useful in aggregate or post hoc, yet still provide too little before-call information to support reliable selective use. We introduce RAISE (Reward-SNR Actionability in Signal Evaluation), a pre-routing diagnostic framework for testing whether available evidence supports selective use before committing to a routing strategy. We instantiate RAISE with Structured Hypothesis Embeddings (SHE), a frozen-LLM intent signal for recommendation using one LLM call per user, and evaluate it through controlled, retrospective, and fresh-cohort studies and a prospective offline pilot whose audit decisions are frozen before independent outcomes are revealed. Across these settings, predictable incremental benefit, not average lift alone, distinguishes settings with recoverable selective value; deployment additionally depends on cost and operational constraints. Seemingly strong oracle or subgroup gains can disappear under independent evaluation. More broadly, RAISE reframes costly inference as an information-acquisition problem: before paying for an expensive model, tool, sensor, or measurement, first test whether its value is predictable at decision time. This principle motivates cost-aware acquisition in settings ranging from agent tool use and stronger-model consultation to robotic sensing and clinical decision pipelines.