Article
CommunityJev Demos & Experiments
Track or Follow? A Jev-Compatible Multi-Agent Trading System
arXiv paper describing a multi-agent trading system whose agents share only point-in-time stores and answer typed questions through Jev, testing whether LLM judgments of web news track the market's reaction to an event or follow a price move already reported.
- Format
- Article
- Reading time
- 2 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Agents share only point-in-time stores and answer typed questions through the interface of Jev, a hosted typed decision model.
- Code sets every position under a proved bound on how far text can move it.
- Item judgments track announcement-window abnormal returns with a weekly Spearman of 0.119.
- Event types agree with issuers' 8-K filings at AUC 0.833.
- Under attack, decision cards traced 88% of successful attacks to the planted item.
Questions about this entry
Short answers drawn from the linked project or page.
It is a multi-agent trading system built to test whether LLM judgments of web news track the market's reaction to the reported event or follow it. Its agents share only point-in-time stores, and code sets every position under a proved bound on how far text can move it.
Agents answer typed questions through the interface of Jev, a hosted typed decision model. A Jev-compatible reader was also built from a pinned LLM's option probabilities for the hash-committed test.
At a weekly horizon, the confirmatory test detects no rank information over code-only features.
It measures the rank association between item judgments and announcement-window abnormal returns, and the paper reports it also holds after the LLM's release.
Under attack, decision cards traced 88% of successful attacks to the planted item.
Much web news about listed firms is published after, and about, the price move it reports, so a reader can agree with the market by following it instead of reading the event. The paper asks which of the two LLM judgments do.
Exploratory analyses show 72% of earnings news items appear after the issuer's filing, contributor-written items often report the price move, and from the first trade after publication the association falls to 0.023.
More Jev resources like this
Jev-AD pairs Jev, a typed decision model that answers predefined questions with probabilities rather than generated text, with a language world model that predicts how nearby vehicles move over the next two seconds for every candidate action. Evaluated in simulated highway merging and 500 replayed NGSIM episodes.
Jev Demos & ExperimentsArticle#arxiv#research#agents
Community
Hugging Face dataset of 80 generated rollout videos (422 MB) supporting studies on Jev-routed temporal granularity for causal video generation, produced with Causal-rCM on Tesla T4 and A100 GPUs.
Jev Demos & ExperimentsVideo#research#video#demo
Community
arXiv study adapting an online shopping experiment to three decision models, including Jev, to test whether digital nudges steer non-generative System One models. Reports 600 runs per model and compares default and social-influence choices against a control.
Jev Benchmarks & EvaluationsArticle#arxiv#evaluation#research
Community
A Hugging Face Space by abidlabs that finetunes a Jev-style spam decision model and tracks the run with Trackio. The Space is hosted on Hugging Face and sleeps after inactivity.
Jev Demos & ExperimentsPlayground#demo#classification#madewithjev
Community
A Japanese-language experiment workspace that asks Jev, through typesafe-sdk-python's jev-latest, why a dummy restaurant's sales fell, and compares Jev against a local Ollama model on accuracy, speed, answer variance, confidence, and cost.
Jev Demos & Experiments#github#python#demo
Communitytaiki00wo/jev-playground
arXiv study that evaluates ride-hailing rebalancing policies under the EU Platform Work Directive's disclosure requirement, using self-interested LLM driver agents built on Claude Haiku 5.5 and Jev in a three-zone model and in Manhattan.
Jev Benchmarks & EvaluationsArticle#arxiv#research#agents
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.