eess.SPOct 3, 2026

System One Models for Wireless Decision-Making:Applications and Performance Evaluation

Authors: Masoud Rahimi, S. M. Matin Alemohammad, Hamid Behroozi, Mahdi Nouri

Organizations: Department of Electrical Engineering, Sharif University of Technology, Tehran 1458889694, Iran

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Many wireless control tasks require repeated selection of a single action from a finite feasible set under stringent latency and reliability constraints. While large language models (LLMs) have recently emerged as general-purpose decision engines, their autoregressive generation mechanism is not naturally aligned with such bounded control problems. This paper investigates System-One models, which directly learn probability distributions over explicitly defined decision spaces, as a lightweight alternative for wireless decision-making. We formalize their decision structure and learning objective, identify their applicability across physical-layer control, radio resource management, mobility, network slicing, and network operations, and evaluate their practical behavior through representative wireless case studies. Using Jev as a System-One implementation, we benchmark decision quality and client-observed latency against generative LLMs and conventional baselines. In receive-antenna selection, Jev delivers up to an 8.5x reduction in median response latency relative to the evaluated LLMs, although this gain comes with a loss in decision quality compared with stronger task-specific alternatives. More notably, in intent-conditioned RAN slicing, Jev achieves utility comparable to the evaluated LLMs while providing more than a 3.5x reduction in median response latency. Complementary evidence from edge-service orchestration further shows that faster decisions do not necessarily translate into lower end-to-end service latency. These results expose a fundamental quality/latency tradeoff and position System-One models not as replacements for numerical optimization, but as a promising decision interface for latency-sensitive, bounded, and intent-driven wireless control.

Figures & tables

Fig. 1: Reported quality on two production decision tasks evaluated by Deel. The first panel reports approved-answer matching accuracy; the second reports expense-categorization agreement with human reviewers. Results were published by TypeSafe AI [ 18 ] .
DecisionRepresentative stateAdmissible outputTypical timescalePrincipal System-One value
Link adaptationSINR/CQI, HARQ history, rank, mobilityMCS or link-configuration indexSlot to tens of msReliability-aware distribution and conservative fallback
Beam selectionPartial CSI, position, angles, past beamsBeam or top- kk beam subsetBeam-coherence dependentAdaptive candidate-set size from confidence
Scheduling/RRMChannels, queues, deadlines, slice KPIsPolicy, user group, or candidate scheduleSlot to near-RTRapid choice among constrained profiles
HandoverSignal histories, velocity, load, QoSStay or target cellTens of ms to secondsExplicit ambiguity and safe defer/measure action
Slice admissionResource state, SLA, predicted demandAccept, reject, defer, or templateSeconds and aboveTyped decision with feasibility screening
Anomaly responseKPI/alarm history, topology, security eventsMonitor, isolate, throttle, rollback, escalateNear-RT to managementRisk-aware mitigation and abstention
TABLE I: Representative bounded decision opportunities across the wireless stack.
Fig. 2: Mean relative capacity loss with respect to exhaustive search for receive-antenna selection.
Fig. 3: Client-observed response latency of the AI methods for receive-antenna selection.
Fig. 4: Client-observed response latency of the AI methods for intent-conditioned RAN slicing.
Fig. 5: Decision quality for intent-conditioned RAN slicing.
Fig. 6: Decision latency for edge-service orchestration. Data from [ 29 ] .
Fig. 7: Service completion for edge-service orchestration. Data from [ 29 ] .
More in this topic

Wireless Resource Allocation

Wireless resource allocation assigns spectrum, power, beams, and computing capacity to meet throughput, latency, fairness, and energy goals.

See all 175 papers

Explore similar work

CardsList
Oct 15, 2026

System1-Arena: Which Decisions Can Be Left to System 1?

Large language models (LLMs) often make discrete decisions, such as flagging phishing or escalating to a human. System-1 models, such as Jev and the OpenAI Decisions API, return probabilities over options in a single forward pass, while System-2 approaches generate reasoning steps. Which decisions can System-1 models handle, and which require generative reasoning? We introduce System1-Arena, a benchmark that gives all models the same decision requests and scores their probabilities. It contains 92k questions across 105 tasks from 268 public sources, in four groups: text classification and knowledge, applied decisions, evaluation and control, and agent and action. It also includes 138 closed-loop environments, from web shopping and SWE-bench coding control to robotics, games, and driving; in real-time mode, the world evolves while a model decides. We evaluate 30 models: 7 closed LLMs, 13 open LLMs read at the answer token, and 10 System-1 models. The largest System-1 models match or exceed fast closed LLMs in non-agentic accuracy, with better-calibrated probabilities at one-quarter of the latency. A reasoning LLM is the most accurate, at about 70x the cost of a fast LLM. In closed loops, large open LLMs succeed most often (up to 32.9%); small System-1 models rarely succeed.

Tianyu Chen, Xinyang Liu, Ruyi An +2

The University of Texas at Austin

LLM Decision-MakingLLM EvaluationEfficient Language Model Inference
AskPDF
Oct 13, 2026

Jeva: System One Models from First Principles

System one models like Jev enable direct, low-latency decision-making. Yet recent open-source practice of predicting an answer from serialized text does not, by itself, respect the structure of a decision problem. We argue that current designs underemphasize four important structural requirements. (i) null-aware: Models should distinguish answer absence from uncertainty among candidates; (ii) permutation-invariant: Reordering alternatives should not change the decision; (iii) option-scalable: Growing candidate sets should not require redefining the output space; (iv) cacheable: Request-independent computation over recurring alternatives should be reusable across requests. We introduce Jeva, a decision-native architecture that addresses these requirements jointly. A shared encoder independently represents the request and each option, while a compact decision stack refines only the request state against immutable option memory. Symmetric aggregation yields permutation-equivariant probabilities; shared scoring accommodates variable-size candidate sets. A separate coverage estimate distinguishes answer absence from candidate competition, enabling explicit null outcomes. Request-independent option representations and layer projections support reuse across newly assembled sets. These mechanisms unify Choice, Noul, and Score outputs. Across evaluations against Jev and open source models, Jeva combines strong typed-decision performance with near-perfect null detection and no decision flips under any tested permutations. It scales to thousands of candidates and substantially reduces latency through cross-request reuse without changing decisions.

Qi Li, Xinchao Wang

National University of Singapore

LLM Decision-MakingEfficient Language Model InferenceSelective PredictionPermutation-Invariant Learning
AskPDF
Oct 12, 2026

Releasing the Inner Jev: A Simple Recipe for Open Decision Models

LLM-based decision-making systems, also called System One models, have recently gained popularity, most notably through Jev (Almeida, 2026). Given a typed input state, a question, and a set of options, they return a probability for each option in a single forward pass, without text generation. We show that existing open instruction-tuned language models can achieve comparable performance without any additional training, by reading out answers from letters (A, B, C, etc.) in the model's output logits at the last token position. Furthermore, we show how a simple supervised fine-tuning recipe can improve their performance further. We evaluate four open instruction-tuned language models: Gemma 4 31B, Gemma 4 12B, Qwen3.6-27B, and Qwen3.5-4B. We fine-tune each using LoRA and a decision head initialized from a slice of the language model head. Furthermore, we introduce OpenDecisions, a novel 2,352-question validation dataset designed to reflect the task composition of JevBench (JevBench main- tainers, 2026) and which computes a Capability score based on accuracy and calibration metrics. Without fine-tuning, Gemma 4 31B scores 79.6 on OpenDecisions, compared to Jev's 80.1. After undergoing our fine-tuning recipe, it scores 84.4 on OpenDecisions and 81.5 on JevBench v1.7, outperforming Jev by 4.3 and 4.4 Capability points respectively and setting a new state-of-the-art on OpenDecisions. On a suite of public decision datasets, our models achieve accuracy comparable to Jev, with lower calibration error. Our results show that open language models already possess System One capabilities, and with simple fine-tuning they outperform Jev on a wide range of decision tasks. We release our models, serving code, and OpenDecisions.

Jonathan Geuter, Andrew Cheng, David Alvarez-Melis

Harvard University · Kempner Institute

LLM Decision-MakingLLM Fine-TuningDiscrete Choice Modeling
AskPDF