# Can Jev be Your Q or Policy in Reinforcement Learning?

arXiv: https://arxiv.org/abs/2610.11692 · HTML: https://mlsanity.com/paper/2610.11692/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

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

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods](https://mlsanity.com/paper/2404.00282/) (2024)
- [Policy Expansion for Bridging Offline-to-Online Reinforcement Learning](https://mlsanity.com/paper/2302.00935/) (2023)
- [Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents](https://mlsanity.com/paper/2311.13373/) (2023)
- [Efficient Reinforcement Learning with Large Language Model Priors](https://mlsanity.com/paper/2410.07927/) (2024)
- [JEV-as-a-Judge: Accept When Confident, Escalate When Unsure](https://mlsanity.com/paper/2609.26550/) (2026)
- [Type-Safe Is Not Error-Free: Typed Decision Models Follow the Option Name, Not the Definition Bound to It](https://mlsanity.com/paper/2609.26758/) (2026)
- [MaestroMotif: Skill Design from Artificial Intelligence Feedback](https://mlsanity.com/paper/2412.08542/) (2024)
- [Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents](https://mlsanity.com/paper/2609.23986/) (2026)
- [Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev)](https://mlsanity.com/paper/2609.24052/) (2026)
- [How Can LLM Guide RL? A Value-Based Approach](https://mlsanity.com/paper/2402.16181/) (2024)
- [Jev for Scientific Decisions: Evaluating Semantic Choices and Their Consequences](https://mlsanity.com/paper/2609.24965/) (2026)
- [Evaluating Decision Models for Text Annotation in Computational Social Science](https://mlsanity.com/paper/2609.24574/) (2026)
- [REFLEX with Jev for Efficient Selective Control in LLM Agents](https://mlsanity.com/paper/2609.26532/) (2026)
- [Can Jev Judge Radiology Reports? Evaluating a System One Model for Clinical Factuality](https://mlsanity.com/paper/2609.27607/) (2026)
- [Same Scores, Different Decisions: Evaluating JEV and Language Models for Legal Document Understanding](https://mlsanity.com/paper/2609.27678/) (2026)
- [Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions](https://mlsanity.com/paper/2609.28613/) (2026)
- [Replacing Large Language Models with Jev Decision Models for Low-Latency Edge Service Orchestration](https://mlsanity.com/paper/2609.22753/) (2026)
- [Visual Jev: Accurate and Efficient Decisions from Shared Visual Context](https://mlsanity.com/paper/2609.25845/) (2026)
- [Open-Jev Judgments on CallScreenBench: Calibrated One-Pass Scam Screening with a Small Language Model](https://mlsanity.com/paper/2609.23959/) (2026)
- [this-that-model-1.0: A typed decision model that decides in 30 ms, for a millionth of a cent](https://mlsanity.com/paper/2609.23886/) (2026)
- [Fast Intent-Driven Service Orchestration with Jev for 6G Edge Networks](https://mlsanity.com/paper/2609.23136/) (2026)
- [JEVQA - Video Quality from Metadata, Bitstream, and Pixel Features with a General-Purpose Decision Model](https://mlsanity.com/paper/2609.24395/) (2026)
- [Natural Language Reinforcement Learning](https://mlsanity.com/paper/2411.14251/) (2024)
- [JEV-Star: Fast, Low-Cost StarCraft II Control with Language-Model Planning](https://mlsanity.com/paper/2609.27331/) (2026)
- [KITE: Scaling Jev Population Experiments with Sparse Flagship Calibration](https://mlsanity.com/paper/2609.27535/) (2026)

## Abstract (arXiv)

Foundation models supply reinforcement learning (RL) with priors that mitigate its longstanding weaknesses in sample efficiency and transfer, but their token-by-token generation makes queries sequential and costly. Jev, a recently released decision model, generates nothing and returns calibrated, typed answers in a single forward pass. Existing work studies foundation models in RL either as models to be trained or as generators to be prompted, and Jev belongs to neither category, having so far served only as a black box in single domains. How well such a model decides on its own in RL environments, and how it can improve RL as a component of training, therefore remain unaddressed. To this end, in this paper we first examine the requirements that the objects of an RL system place on the answers they consume, and establish that Jev can fulfill all of them except the cardinal use of a value function. The remaining objects form positions that admit several roles each. We then construct algorithms that employ Jev at three of these positions, as a reference policy, an exploration judge, and a replay rater, to improve sample efficiency, exploration, and learning performance. Across nine MiniGrid tasks and three Atari games, training with Jev outperforms a standard RL learner, including where the learner makes no progress alone, while the model itself remains untrained. To our knowledge, we present the first use of Jev within the RL learning process and establish a frozen decision model as a usable component of RL training, inviting further exploration of how Jev and other advanced decision models can improve RL.