Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2609.05663

What LLM Trading Agents Actually Do in Production: A Six-Month, Population-Scale Record from Two Fleets

T. J. Barton·Chris Constantakis·Patti Hauseman·Annie Mous·Alaska Hoffman·Brian Bergeron·Hunter Goodreau
View original source ↗Read source document ↗Export metadata ↓

Abstract

We present a continuous, population-scale measurement record of autonomous language-model trading agents operating in production across two systems with one design lineage: DX Terminal Pro (3,505 user-funded vaults trading real ETH in Base memecoin markets for 21 days, February to March 2026) and the DXAP live alpha fleet (500 to 599 user-created agents all-history, 91 to 117 concurrently active, trading Hyperliquid perpetuals, June to August 2026). The record spans roughly six months, 7.5M single-model invocations with about 300K onchain actions, and a further 231,638 multi-tool turns producing 14,596 fills. Four findings carry the paper. First, the operating layer determines behavior more than anything written in strategy text: a risk slider explains leverage (+0.425 per level), agent fixed effects absorb 60% of variance, and a leaderboard render boundary causally routes selection (regression discontinuity 1.75x at the top-3 cut). Second, sizing is volatility-blind: median leverage is 5.0x in every volatility sextile, and one posture-slider cell (11% of the book) holds 62% of liquidations. Third, agents capture almost none of the upside they reach: 43.2% of positions saw at least +300 bps of favorable excursion within 24h, yet 49.3% of those closed with a negative trade return; a mechanical bracket recovers +39.0 bps per position. Fourth, neither fleet shows a directional edge. The DXAP fleet is not profitable and trails a matched Hyperliquid retail benchmark (41% vs. 50% roundtrip win rate). A paired-replay league of frontier models on 416 captured production scenarios finds decision quality statistically indistinguishable at this horizon, while choice stability differs sharply across model families. Every headline survives day-clustered inference, permutation nulls, and a common-fee restatement; the paper closes with a 17-rule methodology canon bought with our own retractions.

Explore related subjects

cs.AIcs.CEcs.MA

Keep this discovery

BibTeXRIS

T. J. Barton, Chris Constantakis, Patti Hauseman, Annie Mous, Alaska Hoffman, Brian Bergeron, Hunter Goodreau. 2026-09-04. What LLM Trading Agents Actually Do in Production: A Six-Month, Population-Scale Record from Two Fleets. https://arxiv.org/abs/2609.05663

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

cs.AI subjectcs.CE subjectcs.MA subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related papers

arXiv2026

OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Heuristic Design

Automating heuristic design in complex, experiment-driven domains requires more than iterative mutation of solution algorithms. Current LLM-based evolutionary methods often rely on stochastic mutation loops that lack long-term strategic planning and a formal mechanism to learn from historical failures, leading to inefficient exploration and redundant trials. To address this, we present OR-Agent, a multi-agent research framework designed for automated heuristic design in optimization problems with rich experimental environments. OR-Agent organizes heuristic search as tree-based workflow that explicitly models branching hypothesis generation and systematic backtracking. Furthermore, to address the lack of adaptive learning in current agents, we introduce a hierarchical, optimization-inspired reflection system in which short-term reflections act as verbal gradients, long-term reflections as verbal momentum, and memory compression as semantic weight decay - collectively forming a principled mechanism for governing research dynamics. Extensive experiments on classical combinatorial optimization problems (e.g., TSP, CVRP, bin packing) and simulation-based cooperative driving scenarios demonstrate that OR-Agent outperforms strong evolutionary search baselines. All code and experimental data are publicly available at https://github.com/qiliuchn/OR-Agent.

cs.AI↗
arXiv2026

Summoning the Oracle to Slay It: Mitigating Look-Ahead Bias in Financial Backtesting with Large Language Models

Backtesting large language models (LLMs) on historical financial data is unreliable when their pre-training data include the evaluated events. An LLM trained in 2024 may already encode how stocks moved during 2018-2020. We name this failure parametric look-ahead bias and propose FinCAD, an inference-time adaptation of Context-Aware Decoding that attenuates contributions from memorised historical outcomes without retraining. FinCAD pairs an adversarial bias-discovery pipeline that learns a model-specific memory-activating prior prompt with an entity- and date-adaptive rule that scales the CAD strength using a per-(entity, date) confidence signal. Across five 7-14B LLMs and five mega-cap equities, the largest model-level mean in-sample return correction is -67.1%. For the three larger models, 2025 out-of-sample returns remain within $8K and mean Sharpe within $\pm$0.10 of baseline; mean general-benchmark accuracy remains positive or within -1.7 points for four of five models. On an eleven-model leaderboard, FinCAD raises the subset-averaged in-sample/out-of-sample Spearman correlation from +0.779 to +0.846, yielding rankings that are more closely aligned with post-cutoff performance.

cs.AI↗
arXiv2026

LLM-Aided Design for Manufacturing: A Multi-Agent System for Intent-Preserving Redesign of CAD for Improved Manufacturability

We introduce autonomous, intent-preserving Design for Manufacturing (DFM) redesign of CAD parts: given an engineer's CAD model, the method returns a variant that is easier to manufacture without losing its design intent. Generating such a redesign in a single shot is unreliable, since CAD fidelity degrades as parts grow complex; we instead produce it as a sequence of individually verified design transitions. Our DFM-Redesign pipeline realizes this with two coupled agent subsystems driven by a pretrained multimodal LLM: a DFM Reviewer that inspects the current design and proposes one intent-preserving manufacturability improvement at a time, and a CAD Modifier that executes each proposal as an edit to the part's CadQuery program. The CAD Modifier closes a verification loop, compiling every candidate edit and visually checking it against the intended change from multi-view renderings, then re-generating or re-instructing until the edit is accepted or abandoned. Iterating review and verified modification compounds edits into parts more complex than one-shot generators reliably produce, preserves the original intent at each step, and requires no fine-tuning. On a 46-part benchmark scored by chamfer distance to reference geometries, the CAD Modifier reproduces target parts more accurately on average than chain-of-thought single agents given the same tools, and ablations isolate the contributions of the visual review loop and of captioning the design state before each edit. A centrifugal pump casing built from 32 chained transitions illustrates the complexity reachable by compounding verified edits. This is a preliminary report: evaluation of the full review-and-redesign loop, including manufacturability gain and an operational measure of intent preservation, is ongoing.

cs.CE↗