Open preprints, screened and openly reviewed
PubArx is a community-run repository for research preprints in all disciplines. Every submission is checked by a moderator before it is published with a permanent identifier and metadata designed for Google Scholar. Authors can open their papers to signed review by researchers who sign in with ORCID. Why PubArx exists
How publishing on PubArx works
Submission guide- SubmissionUpload the PDF, list the authors with their ORCID iDs, choose a subject and a licence.
- ScreeningA moderator checks scope, completeness and basic scholarly standards, usually within two working days.
- PublicationThe paper receives a permanent PubArx identifier and metadata for Google Scholar and OAI-PMH harvesters. Indexing by third parties is not guaranteed.
- Open reviewResearchers who sign in with ORCID endorse papers and, if the authors request it, publish signed reviews, tied to each version.
Recent papers
All recent papers-
GradReason: LLMs as Meta-Learners that Replace Training Epochs with Training-Data-Free Weight Updates
Standard training recipes make a fixed number of passes over the training data, even when an epoch mostly adds mini-batch noise. We study whether a large language model (LLM) that reads the weight and gradient history of a run can replace some of these epochs with updates that compute no gradient and read no training image. In GradReason, an LLM agent is called every ten epochs. In a restricted sandbox it analyses recent weight snapshots, epoch-mean gradients and validation metrics, then submits a Python program that computes new weights and a plan marking each of the next ten epochs as data or virtual. A virtual epoch is kept only if it passes a forward-only check on 5,000 held-out validation images. In 120 runs on CIFAR-10 and CIFAR-100 with three architectures, Claude Opus 5.5 used 32.8\% fewer data epochs than the 80-epoch recipe at 0.31 percentage points lower test accuracy (95\% CI $-0.72$ to $+0.09$; 0.94 points on ResNet-18), on the recipe's own frontier of data against accuracy. Unprompted, Opus averaged recent weight snapshots in every run. This choice produced the savings: a fixed rule with the same acceptance check but extrapolations from prior work saved 5.4\% of the data epochs, and the same rule with averaging added saved 25.0\%. The LLM's contribution is to find a working update within a single run; once found, a fixed rule implements it equally well. An Opus run cost 0.68 USD, but at this scale the agent's latency exceeded the GPU time it saved.
-
PIA: Agentic Physics-Informed Runtime Anomaly Detection
Runtime anomaly detectors for cyber-physical systems are either learned as black boxes from normal data, which miss stealthy manipulations that keep every signal inside its normal range, or derived by hand from physical models, which requires expert effort for every plant. We introduce physics-informed agents (PIA), in which a large language model agent writes the detector itself as a set of physical residuals, such as pump characteristics, tank mass balances, and controller logic, and refines every candidate against normal operating data through an evaluation workbench before deployment. The result is a compact, human-readable detector that runs in milliseconds and names the component behind each alarm. On the BATADAL water distribution attack benchmark, PIA with Claude Opus 5.5 reaches an F1 of 0.878 on the test attacks against 0.504 for the strongest of six statistical and deep baselines, keeps detecting attacks concealed by replayed and offset sensor readings, and attributes every detected test attack to the attacked component. Ablations show that testing hypotheses against data is decisive: agents that write residuals from the plant description alone lose up to 0.28 F1, whereas agents that see only anonymized signals recover most of the physical structure.
-
FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning
Federated learning servers combine client models with a fixed aggregation rule, and each rule in common use is designed for one kind of heterogeneity. We study whether a large language model (LLM) that inspects the client models can choose the rule itself, without any training on the server. In FedReason, the LLM is called every ten rounds. It analyses the weights by running code in a restricted server-side sandbox, sees only the printed results, may score a few candidates on a 500-image proxy set, and submits a short Python aggregation program. The server applies the program until the next call and falls back to FedAvg whenever its output is invalid. Full weight tensors never leave the server. We evaluated FedReason with Claude Opus 5.5 on CIFAR-10 and CIFAR-100 with ResNet-18 under Dirichlet label skew, width-heterogeneous sub-models and Byzantine clients, in 168 runs against 14 baselines. Across 12 paired label-skew runs it beat FedAvg by 1.26 percentage points on average (10 wins), and a control that spends the same per-round proxy budget on choosing among standard rules by 1.08 points. It was the strongest server-side rule on CIFAR-100 but did not beat SCAFFOLD, which changes client training. With three of ten clients malicious, it excluded all sign-flipping clients from the first round and stayed about one point below FLTrust without training a root model. Without proxy feedback, accuracy fell from 73.8\% to 38.8\% in one seed. A 60-round run cost 0.79 USD in API fees on average.
-
Multi-Agent Daily Planning System (MADPS): A GAIA-Based Architecture for Dynamic Scheduling
This document outlines the GAIA methodology design for a single-user Multi-Agent Daily Planning System (MADPS) engineered to generate, adapt, and personalize daily schedules. The architecture consists of three core autonomous components: the User Profile Agent (UPA), the Task Management Agent (TMA), and the Planning & Adaptation Agent (PAA). MADPS is designed to maximize priority satisfaction under constraints, minimize re-planning latency and schedule churn during task disruptions, and personalize schedules by learning user energy curves and preference weights. To support these objectives, the system employs FIPA-style interaction protocols and a dual-strategy PAA workflow, utilizing rapid, greedy local repairs for minor schedule disruptions and Genetic Algorithm (GA)-driven global optimization for system-wide impacts. Proposed schedules are evaluated using a comprehensive fitness function that carefully weights priority satisfaction, energy alignment, transition minimization, and hard constraint penalties to ensure feasible and highly optimized daily plans.
-
Smart Contracts as Autonomous Agents: Engineering a Decentralized Naming Infrastructure on the Polygon Blockchain
While traditional multi-agent system (MAS) frameworks such as JADE and SPADE rely on distributed computing environments and asynchronous message passing, "Report-2.pdf" presents a novel paradigm: deploying blockchain smart contracts as fully autonomous agents. This detailed development document chronicles the implementation of the University of Calgary Name Service (UCNS) on the Polygon network, systematically translating abstract GAIA architectural designs into executable Solidity code. The specification provides a comprehensive engineering blueprint, encompassing detailed use case specifications, UML class and sequence diagrams modeling trustless inter-agent protocols, and explicit entity-relationship data structures. By detailing Web3 frontend integration, rigorous testing strategies, and mainnet deployment procedures, this report demonstrates how transaction-based coordination effectively replaces centralized platform mediation. The resulting implementation validates the application of agent-oriented software engineering principles to build secure, immutable, and production-ready decentralized applications
-
Decentralized Naming Services on Polygon: A GAIA-Based Multi-Agent System Design
This document applies the Generic Architecture for Information Availability (GAIA) methodology to design the University of Calgary Name Service (UCNS), a decentralized naming infrastructure operating on the Polygon blockchain. By methodically progressing through GAIA’s requirements analysis, architectural design, and detailed design phases, the report translates high-level operational goals into a structured multi-agent system. The design specifies three distinct roles—Registry Manager, Resolution Provider, and Pricing Authority—and maps them to three singleton smart contract agents: the Registry Agent, Resolver Agent, and Pricing Agent. Detailed specifications for internal agent state, inter-agent communication protocols (e.g., domain registration and ownership transfer), and service implementations are provided to ensure trustless, decentralized coordination. Ultimately, this architectural blueprint bridges theoretical agent-oriented software engineering with practical Web3 implementation, demonstrating the efficacy of GAIA in designing robust, modular blockchain applications.
Submission credits
Each researcher can submit 3 new papers. After that, each published community review allows 1 more submission. New versions of a paper are always free.
- Free submissions
- 3
- Per published review
- +1
- New versions
- free
Earning more submissions
- Choose a paper in your field that is open for review.
- Publish a signed review with a summary and your main concerns.
- The credit is added as soon as the review is public. Reviews hidden by moderators stop counting.
Latest community reviews
No community reviews have been published yet.
Browse by subject
All subjects- Computer Science 12 subjects · 9 papers
- Mathematics 9 subjects · 0 papers
- Statistics 4 subjects · 0 papers
- Physics 7 subjects · 0 papers
- Engineering 7 subjects · 0 papers
- Materials Science 2 subjects · 0 papers
- Chemistry 5 subjects · 0 papers
- Biology and Life Sciences 6 subjects · 0 papers
- Medicine and Health Sciences 5 subjects · 0 papers
- Earth and Environmental Sciences 4 subjects · 0 papers
- Agricultural and Food Sciences 3 subjects · 0 papers
- Economics and Finance 5 subjects · 0 papers
- Social Sciences 6 subjects · 0 papers
- Arts and Humanities 5 subjects · 0 papers
Permanent identifiers
Every paper keeps its identifier and full version history, so it can be cited reliably.
Indexed and harvestable
Pages carry Google Scholar metadata, and the archive is open to OAI-PMH harvesters.
Signed review
Reviews and endorsements are public and signed with the reviewer’s name and ORCID iD.
Free and open
Submitting and reading are free. Authors choose the licence of their work.