Papers for

laboratory automation engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Framework guides microscope decisions to speed experiments and improve learning

Building heterogeneous multistep workflows in automated microscopy: reward design and knowledge transfer for autonomous structure property discovery

Abstract: Autonomous microscopy can turn fast acquisition into scientific progress when it decides not only where to measure, but also what information to acquire, at what scan rate, and when to recalibrate the instrument. We develop a budget constrained framework for such multistep structure-property workflows. It combines explicit scientific rewards, action costs, instrument observation models, transfer of pre experiment knowledge into the online campaign, and evaluation kept independent of the controller. The transferred knowledge includes predictor accuracy and computational cost, empirical learner maturity functions that weight model-derived rewards, and drift characteristics established before controller training. Using a real electron energy-loss spectroscopy dataset, we run two complementary campaigns. In the first, the controller chooses between imaging and spectroscopy, image size, and scan speed. In the second, the instrument drifts and the controller also decides when to recalibrate. The campaigns show that response discovery and structure-property learning favor different surrogate models and acquisition strategies. They also show that simple acquisition rules form strong, practical baselines. Independent error analysis reveals where model uncertainty is and is not a reliable learning signal. In the drift campaign, explicit registration greatly improves positional accuracy, and the framework measures what this costs in spectroscopy throughput. Together, these results provide a reproducible way to design, compare, and audit autonomous experiments, and they define what microscopes must provide for deployment: independently executable actions, characterized scan and detector responses, timestamped registration telemetry, and complete action records.

Sun 8 NovMachine Learning
The gist
Microscopes can collect lots of data, but deciding exactly what to measure and when can be tricky. The authors present a system that helps microscopes make smarter choices during experiments by considering costs, previous knowledge, and instrument changes over time. Their system was tested using real spectroscopy data, showing it can choose different measurement types and know when to recalibrate the microscope to keep results accurate. This approach also helps understand when simple measurement rules work well and where more complex decisions add value.
Open → 2611.11609v1

Adaptive robot control improves squeeze bottle liquid dispensing accuracy

Adaptive Hybrid Force-Vision Control with EMG-Derived References for Deformable Bottle Manipulation

Abstract: Robotic automation of laboratory tasks has become a growing interest to remove researchers from hazardous environments and repetitive procedures. However, even equipment as simple as squeeze bottles poses a challenging manipulation problem due to its deformability. This paper presents an adaptive hybrid vision-force controller for robotic grippers to effectively manipulate laboratory squeeze bottles to dispense liquid. This approach integrates force and vision feedback according to the interaction state, enabling effective squeezing while accounting for bottle deformation and recovery. The proposed controller is validated by comparing its performance with a pure force controller on 12 combinations of conditions consisting of 2 target dispense volumes, 2 plastic squeeze bottles, and 1 to 3 squeezes used to dispense. Human demonstrations of these operating conditions were collected using electromyography (EMG) sensing mapped to a desired grip force, which was then used as the force reference for the controllers to squeeze the bottles. Results demonstrated that the proposed adaptive hybrid vision-force controller achieved more accurate liquid dispensing with a mean absolute error (MAE) of 6.54 mL compared to a MAE of 15.92 mL from the pure force controller, while also replicating the human action recorded from the EMG signal more closely.

Wed 4 NovRobotics
The gist
Handling soft squeeze bottles with robots is tricky because the bottles change shape when squeezed. The authors developed a control system that uses both touch (force) and sight (vision) to better mimic human squeezing. They tested their system against a simpler force-only control and found it dispensed liquid more accurately. They also used muscle signals from humans to guide the robot’s squeezing force.
Open → 2611.07235v1

Improving action design for efficient long-term scientific experiments

Designing Informative Actions: Action Construction for Long-Horizon Research Agents

Abstract: Large language model agents support automated scientific research by connecting literature analysis and planning with experimentation. Evaluating which action an agent selects does not establish which experiment its instruction specifies, because omitted interventions or replication counts leave consequential choices to the executor. We introduce a reading-set framework for evaluating action construction under a common cost rule. Across 30 synthetic states, complete-design requests increase affordable efficiency by 465.98% and 327.91% relative to the action-name baseline in the two model families, respectively. An author-constructed research-action evaluation dataset provides 60 scenarios for complementary judgment evaluation. On this dataset, the scenario-level information-per-cost measure has a mean within-scenario correlation of 0.733 with judgments from 18 human participants. The framework makes design specification and execution ambiguity measurable, providing a reproducible basis for assessing how research agents translate scientific intent into informative, budget-feasible experiments.

Sat 31 OctArtificial Intelligence
The gist
Figuring out the best step an AI should take during a long scientific project can be tricky because the instructions may leave important details unclear. The authors developed a method to measure how well AI agents specify their actions, focusing on making experiments both informative and affordable. They tested this method in synthetic setups and found it helped AI plans be much more efficient. They also compared AI judgments to human opinions, showing good agreement. This work helps ensure AI-driven experiments are clear and effective within budgets.
Open → 2611.00773v1

Scientific intelligence evolves through linked laboratory experiments

Evolving Scientific Intelligence: From Fragmented Evidence to Distributed Experimental Loops

Abstract: Scientific discovery advances when evidence from different investigations is brought into contact. Yet paper-centric communication leaves experimental results fragmented, delayed, or unreported, creating a "scientific memory wall" between growing computational capabilities and the evidence accessible to AI systems. We envision a different dynamic: in a network of intelligent laboratories, a failed or overlooked experiment in one domain could trigger a hypothesis in another, whose testing generates evidence that stimulates further investigations. Such chains of information collision and empirical validation could transform isolated discovery loops into a cumulative scientific process. We propose Evolving Scientific Intelligence (ESI), an architectural blueprint for enabling these evidence-driven chain reactions. ESI preserves experimental records in shared, computable scientific memory, where evidence from different domains can be recombined into testable hypotheses. It jointly selects candidates and evaluation methods according to scientific value, reliability, and cost, then coordinates physical tests across distributed experimental nodes. Their feedback revises hypotheses and evaluators, while slower meta-control reassesses research objectives and decision criteria to guard against self-reinforcing errors and misguided optimization. We call for an Information Manhattan Project to build the infrastructure for scientific intelligence that evolves through experimentally grounded chains of discovery.

Sat 31 OctArtificial IntelligenceMachine Learning
The gist
Scientific progress slows because important experiment results are scattered across many papers and sometimes not shared quickly or at all. The authors propose a new system where intelligent labs share their results in a connected, searchable way that lets experiments from one area inspire new tests in another. This back-and-forth, guided by shared goals and careful checks, could help discoveries build on each other faster. They call for big new infrastructure investment to build this kind of evolving scientific network.
Open → 2611.00580v1

Operon-S1 speeds up decision making for biology language agents

Operon-S1: a fast decision controller for long-horizon biomedical agents

Abstract: Language-model agents now carry out long scientific work in biology, but their judgements about conventions, skills, errors, evidence and stopping are made inside the reasoning that does the work, where they cannot be measured, replaced or improved on their own. Here we present Operon-S1, a fast decision system, a System 1 for the agent, that separates judging from doing. A decision harness poses the agent's recurring judgements as closed questions at 13 decision points and acts only through fixed messages that never contain an answer, so any model that answers the questions can serve as the judge. Across seven life-science benchmarks, a local decision model took over these judgements in 0.6 s at the median for an in-loop request on CPU at no request cost, with no measurable change in the agent's score on five of six benchmarks, whereas the general language model that drives the agent, asked the same questions, accounted for 8.0% to 35.2% of task cost. Every decision is recorded with its consequence. Retraining on labels from task construction, verifiers or execution raised decision accuracy on every question in each of three trained versions, and a new version enters service only through a promotion gate. Task-level results in this study use the public checkpoint. The same closed decisions serve wet-laboratory protocol troubleshooting and the design of a germline target enrichment panel. Like the regulator of an operon, which switches genes on and off without making their products, Operon-S1 steers the agent without doing its work, and makes the agent's judgements a layer that can be measured, replaced and trained.

Fri 30 OctArtificial IntelligenceMachine Learning
The gist
Working with complex biological tasks often requires language-based AI agents to make many small decisions during their reasoning process. These decisions are usually made internally, which makes them hard to improve or measure directly. The authors created Operon-S1, a quick decision controller that separates judgment from action by posing specific yes/no questions. This system speeds up judgments dramatically without losing accuracy and allows decisions to be retrained or replaced independently from the agent’s main reasoning. Like a biological system that controls gene activity without producing proteins, Operon-S1 guides the agent without doing the work itself.
Open → 2610.41350v1

Self-driving laboratories made auditable with unified safe control framework

Making Self-Driving Laboratories Auditable:A Unified Framework for Hybrid Actions,Measurements, and Safe Execution

Abstract: Self-driving laboratories (SDLs) are laboratory systems that couple experimental planning, automated execution, and measurement feedback in a closed loop. Integrating flexible robot control with the typed application programming interfaces (APIs) and continuous measurements exposed by laboratory instruments remains an execution-interface challenge. To address this challenge, we propose a traceable framework comprising four components: LAM (Lab Action Model), OpenSDL, Safe-SDL, and L3-Bench. LAM is a proposed measurement-conditioned policy architecture that extends vision-language-action paradigms to generate both continuous robot trajectories and typed instrument API calls. OpenSDL is an execution substrate with an initial control implementation, designed to map role-level operations to heterogeneous devices, coordinate execution, and record timestamped causal events. The proposed Safe-SDL runtime gate combines pre-dispatch schema and resource checks with signal temporal logic monitoring during execution, including extended waiting periods. L3-Bench (Level-3 Laboratory Benchmark) specifies an episode-level evaluation protocol covering physical outcomes, timing, reproducibility, safety violations, and fault recovery. Together, these components provide an end-to-end design for linking hybrid action generation, monitored device execution, measurement feedback, and experimental evaluation, addressing coordination and traceability challenges in SDL workflows.

Tue 27 OctRoboticsArtificial Intelligence
The gist
Self-driving laboratories automatically plan and run experiments using robots and machines, but controlling different devices safely and tracking what they do is hard. The authors propose a new system that coordinates robots and instruments while keeping detailed logs of every action and measurement. Their framework also checks in real time to ensure safety rules are followed and measures how well experiments perform and recover from problems. This approach helps make automated labs easier to monitor, understand, and trust.
Open → 2610.36761v1

Semantic digital twin bridges ai and real labs for safer experiments

Semantic Representation for Agentic Self-Play in Automated Laboratories

Abstract: Navigating complex, high-dimensional biological search spaces necessitates scalable physical and computational intelligence to explore beyond local optima through iterative self-play across ideation, experimentation, and automation. Translating experimental designs into reliable physical execution remains bottlenecked by static laboratory automation and unmodeled physical variability. To address this, we introduce VERified Infrastructure for Discovery Laboratories, or VERID, a foundational infrastructure designed to bridge the gap between the high-level reasoning of artificial intelligence (AI) agents and complex, error-prone physical realities of wet labs. VERID is a persistent, high-fidelity semantic digital twin of the laboratory workcell that provides four core services: queryable introspection for agentic reasoning, time-compressed simulation for protocol validation, comprehensive trace persistence for a complete scientific record, and a framework for safe execution. We present three case studies using aqueous dye and deionized water mixtures to validate the optical and fluidic foundations of VERID. These studies demonstrate how VERID enables pre-emptive detection of critical errors in experimental protocols, stateful mid-run error recovery and post-hoc identification of subtle physical failures. The simulation functions as a discrete accounting engine, allowing agents to safely and inexpensively explore experimental designs in silico and refine experimental strategies through iterative self-play. VERID also captures structured multimodal experimental data for downstream analysis, knowledge mining and agent training. We argue that this semantic layer is an essential prerequisite for deploying autonomous agents in the biochemical and biomedical sciences, ensuring data integrity, operational safety, and paving the way for tackling previously intractable grand challenges in biology.

Fri 23 OctRoboticsArtificial Intelligence
The gist
Doing experiments in biology can be tricky because physical labs have lots of unpredictable stuff going on. The authors created VERID, a virtual copy of a real lab that helps smart AI agents plan and check experiments before running them for real. This digital twin can spot mistakes early, recover from errors during experiments, and store detailed records for later study. Their tests with water and dyes show how this system helps run safer and smarter biological experiments.
Open → 2610.32755v1

Self-building labs create flexible robot experiment setups automatically

Self-Building Labs

Abstract: Self-driving laboratories (SDLs) accelerate scientific discovery by automating experimental execution and optimization. AI agents can increasingly propose new experiments, but existing SDLs can only run the procedures they were built for. Adapting them to a new experiment still takes extensive manual engineering, which makes laboratory flexibility the bottleneck for scaling discovery. We introduce the self-building laboratory (SBL), which designs, configures, and operates its own laboratory setup given a high-level scientific goal. SBL starts from whatever already exists, from an empty room to a working SDL, and builds the missing capabilities: the lab layout, its digital twin, robot skills, and experimental workflows. We demonstrate the system working across different robots and setups, scaling from a single workstation to laboratories with several robots working together. We validate SBL's end-to-end capabilities through a real-world quantum-dot synthesis experiment. By shifting the role of human researchers from manually configuring and programming device automation to specifying scientific objectives, SBL makes scientific automation more accessible, flexible, and scalable. Project website: https://self-building-labs.github.io/

Fri 16 OctArtificial IntelligenceMultiagent SystemsRobotics
The gist
Usually, labs with robots can only do experiments they were set up for, and changing them for new experiments takes a lot of work. The authors designed a system called self-building laboratory (SBL) that can start from scratch or an existing lab and figure out how to build and run the right setup automatically. This includes designing the layout, programming robot actions, and organizing experiments based on a scientist’s goals. They tested SBL on real chemistry experiments involving tiny particles and showed it can work with multiple robots. This way, scientists just say what they want to study, and the lab builds itself to do it.
Open → 2610.23826v1

Multimodal benchmark measures AI skill in lab decision making

LabOPBench: A Multimodal Benchmark for Evidence-Grounded Laboratory Decision Making

Abstract: Laboratory experiments involve more than following predefined protocols; they require adaptive decision-making as the experimental state changes. Existing scientific benchmarks rarely assess such evidence-based decisions in laboratory settings. Here we present LabOPBench, a multimodal benchmark of 756 expert-authored, independently reviewed questions in organic synthesis and materials science. Each item pairs laboratory evidence with procedural context and an open-ended judgment, evaluated using a question-specific scoring rubric. Eight multimodal models obtain overall normalized scores of 28.8-45.8%, leaving substantial room for improvement. On a controlled 100-question subset, the strongest models outperform undergraduate participants on average but remain below the average performance of PhD participants. Expert analysis of responses from the three leading models identifies Evidence Misreading and Evidence-Decision Conflict as the dominant error patterns. These results reveal that current models still struggle to turn multimodal perception into reliable laboratory decision-making.

Wed 14 OctArtificial Intelligence
The gist
Laboratory experiments don't just follow fixed steps; they need careful choices based on changing evidence. The authors created LabOPBench, a test with real lab questions requiring these decisions and combining different types of information. They found current AI models still struggle, scoring low compared to expert humans. The biggest problems are misunderstanding evidence or conflicting it with decisions. This shows AI has a long way to go before it can reliably help in real lab work.
Open → 2610.19780v1

LabCompiler improves reliable lab workflows from imperfect protocols

LabCompiler: A Framework for Verifiable Human-Machine Laboratory Execution from Imperfect Protocols

Abstract: Closing the loop of AI-driven science requires reliably translating natural-language protocols into executable laboratory workflows despite protocol defects and heterogeneous hardware. Existing approaches often couple scientific interpretation with device-specific code generation, making errors difficult to localize and limiting reuse across laboratory platforms. We introduce LabCompiler, a robust protocol-to-execution framework that transforms imperfect natural-language protocols into verifiable human-machine workflows. Its protocol firewall diagnoses and repairs defects before compilation while preserving unaffected content, guided by troubleshooting knowledge accumulated through perturbation-guided self-evolution. A two-level, device-agnostic graph representation separates experimental semantics from hardware-specific implementation and supports capability-based device assignment with coordinated human execution. We further introduce a protocol recovery benchmark covering four controlled perturbation types and naturally occurring errors collected from protocols written by iGEM participants. Experiments show that LabCompiler outperforms frontier LLMs in protocol error correction while enabling coordinated human-machine execution across heterogeneous, partially automated laboratory settings.

Wed 14 OctArtificial Intelligence
The gist
Laboratory experiments often start with instructions written in natural language, which can have errors or unclear steps. The authors developed LabCompiler, a system that detects and fixes these errors automatically before turning the instructions into steps that humans and machines can follow together. LabCompiler works across many types of lab devices by separating the experiment’s meaning from the hardware controls, making it easier to reuse and verify workflows. The authors tested their system on various errors and found it better at fixing them than leading language models, enabling smoother cooperation between humans and machines in real labs.
Open → 2610.19550v1

AI improves each step of angle resolved photoemission spectroscopy workflow

Progress and Prospect of AI in ARPES Workflow

Abstract: Artificial intelligence (AI) is becoming an increasingly useful tool across the experimental sciences, including angle-resolved photoemission spectroscopy (ARPES), which routinely produces large, multidimensional datasets of electronic structure. Recent advances in AI and machine learning (ML) have opened new opportunities across the entire ARPES workflow, from automated sample preparation and real-time data acquisition to post-experiment data analysis and comparison with theoretical calculations. Despite this progress, a comprehensive review of ML applications, their capabilities, and reliability across the different stages of ARPES workflow is still lacking. In this review, we first introduce ML methods that are most relevant to experimentalists working in condensed matter physics and materials science. We then follow the ARPES workflow, reviewing existing ML applications at each step and discussing their advantages, limitations and potential for future development. We also examine the current ARPES data landscape, where several open databases are available but remain relatively small and fragmented compared with large, shared datasets such as ImageNet. Given these limitations, we suggest that the community focus on sharing pretrained models that can be further trained, adapted to specific tasks, and redistributed, while working toward a larger and standardized open ARPES dataset repository. Finally, we discuss our perspectives on the future of AI within the ARPES workflow using a six-level framework of laboratory automation, highlighting the opportunities and challenges in moving toward a fully autonomous, self-driving ARPES laboratory.

Wed 7 OctMachine Learning
The gist
Angle-resolved photoemission spectroscopy (ARPES) is a technique that creates large and complex data about materials’ electronic properties. The authors review how artificial intelligence and machine learning help automate and improve all parts of ARPES, from preparing samples and collecting data to analyzing results and comparing them with theory. They highlight current challenges, like small and fragmented datasets, and suggest sharing trained AI models and creating larger, standardized data repositories. They also describe a future vision of a fully automated ARPES lab controlled by AI.
Open → 2610.10140v1

AI system checks lab equipment setup for liquid handling robots

A Passive AI System for Verifying Physical State on Automated Liquid Handlers

Abstract: Automated liquid handlers execute digital protocols, but operators must assemble the deck and confirm that the physical setup matches the intended experiment. We present the Labware Setup Checker, a passive vision system that verifies deck preparation on an Opentrons Flex without modifying its hardware or firmware. A consumer webcam mounted outside the robot supplies images to a browser application. The checker segments the deck into slots, corrects slot assignments using the known deck geometry, classifies the labware, and compares the observed setup with a reference protocol library to report missing, misplaced, or unexpected labware. It operates independently of the robot controller and does not interrupt or gate a run. During SwabSeq Respiratory Viral Panel (RVP) pre-PCR deck preparation, the checker tracked a slot from empty to a base and then to the completed plate-and-base assembly, identifying the completed assembly in all 29 frames before robot motion. Across these frames, 95.1% of the 348 labware classifications for slots requiring exact matches agreed with the protocol reference. In 480 frames with partially occluded reservoirs, all 6,720 slot assignments were correct. Across three camera positions and two lighting conditions, slot assignment was 100% correct, and 97.73% of labware classifications matched the protocol reference. Median verification time was 2.10 s on a laptop using only its CPU and 4.24 s from frame capture to receipt of results during AWS deployment in the laboratory. These results show that an external camera and independent software can provide verification of deck setup against protocol requirements within seconds, allowing operators to review the physical setup before starting a run.

Fri 2 OctRobotics
The gist
Automated tools that handle liquids in labs need correct physical setups before running tests, but humans must verify these setups. The authors propose a system that uses a simple camera and AI software to confirm that the physical labware matches the experiment instructions without stopping the robot. Their system watches the setup, identifies lab pieces accurately, and quickly reports any mistakes. This helps ensure experiments start properly without manual double-checking.
Open → 2610.02668v1

Tool and robot control jointly design improve powder weighing accuracy

Tool-Policy Co-Design for Powder Weighing in Laboratory Automation

Abstract: Autonomous powder weighing is one of many bottlenecks in laboratory automation due to the complex, non-linear dynamics of heterogeneous materials. Robot chemists performing this task utilise standard tools shaped for the dexterity of human hands, whose fixed geometry sets the dynamics that the control policy needs to regulate. This work introduces a tool-policy co-design framework that concurrently optimises the morphology of a dispensing tool and its control policy for use by robots in chemistry laboratories, formulated as a bi-level optimisation that minimises dispensing error over a target distribution of powder flowabilities. The outer loop varies tool-design parameters such as tool depth, width and rim spike topology using Bayesian optimisation and hyperband, while an inner loop optimises a control policy for each candidate morphology. We also introduce a geometric similarity metric that warm-starts policy training from cached policies of structurally similar designs, exploring 28% more configurations under the same compute budget. The proposed framework is evaluated on a robotic powder weighing task across seven materials with distinct physical dynamics in a flowability-informed robot-material simulation framework. Experimental results demonstrate that our co-designed tool morphology reduces real-world weighing errors by 45% relative to a standard tool, including on previously unseen materials. These results demonstrate our method can adapt both the control policy and the physical tool to the dynamics of the target material, bringing a new paradigm for material manipulation to the field of laboratory automation.

Wed 30 SeptRobotics
The gist
Weighing powders accurately is hard for robots because powders behave in complex ways and tools are normally designed for people. The researchers created a method that designs the tool itself and how the robot controls it at the same time. This method tries many tool shapes and control settings to find the best combo that works well for different powders. Their approach reduced weighing errors by almost half compared to using a regular tool, even for powders the system hadn’t seen before.
Open → 2609.39797v1

Hierarchical planning improves tool coordination across isolated servers

HTN Planning as a Coordination Layer for Multi-Server MCP Tool Orchestration

Abstract: The Model Context Protocol (MCP) isolates servers by design: only the host can orchestrate cross-server workflows. When the host is a large language model, the resulting orchestrations are non-deterministic, non-reproducible, and pay one inference round-trip per tool call. We present a coordination architecture in which a Hierarchical Task Network (HTN) planner generates a verifiable cross-server plan once, and a runtime middleware executes it deterministically across multiple MCP servers, binding cross-action data dependencies via a template mechanism (\verb|${context.X}|) substituted at execution time. The architecture mirrors MCP's isolation constraint: each compound task decomposes into server-local primitive actions, and inter-server data flow is bound at execution time via JSON-path output extractors. We instantiate the architecture on five HTN domains spanning laboratory robotics, bioinformatics and multiscale modelling, and demonstrate end-to-end execution from a browser-based plan controller against eight live third-party MCP servers querying real biological databases.

Sun 27 SeptArtificial Intelligence
The gist
When computers need to work together but are kept separate for safety or organization, it can be hard to direct their teamwork smoothly. The authors introduce a method that designs a clear step-by-step plan beforehand, then runs this plan steadily across different servers without confusing overlap. This approach helps avoid random mistakes and speeds things up by cutting down back-and-forth communication. They tested their system in real science-related tasks, showing it works for complex jobs involving multiple tools and databases.
Open → 2609.33731v1

Ai systems improve managing scientific computing workflows and reproducibility

AI-Driven Scientific Computing Workflows: A Systems Review of Orchestration, Execution, Reproducibility and Provenance

Abstract: Artificial intelligence (AI) is increasingly embedded within scientific computing workflows that combine simulation, data processing, optimisation, visualisation and experimental or observational components. Learned models may serve as explicit workflow components, retain persistent state and, in adaptive settings, influence subsequent computation. Existing work has characterised scientific workflow management systems, dynamic and steered workflows, AI--HPC coupling motifs and the machine-learning lifecycle, although these areas are often discussed separately. This review brings them together from a systems perspective. We distinguish conventional scientific workflows, machine-learning pipelines, AI-coupled high-performance computing (HPC) workflows and broader automated research workflows, and propose a continuum describing the depth of AI participation from a computational stage to co-adaptive workflow control. The associated systems requirements are organised around five concerns: control and orchestration; compute and execution; data and model state; reproducibility and provenance; and governance and assurance. Representative systems and applications include AI-steered molecular simulation, drug and materials discovery, simulation--surrogate coupling and distributed self-driving laboratories. Workflow-level evaluation is considered in terms of scientific progress, execution cost, data movement, resource use, resilience and decision traceability. We conclude by identifying open problems in dynamic workflow representation, state-aware recovery, heterogeneous scheduling, interoperable data planes, model-mediated decision provenance and reproducible adaptive execution.

Fri 18 SeptDistributed, Parallel, and Cluster Computing
The gist
Scientific computing combines many steps like simulations, data analysis, and experiments. The authors reviewed how artificial intelligence (AI) helps manage these complex workflows, making them more adaptive and efficient. They organized systems needs around control, execution, data handling, reproducibility, and trust. The paper highlights uses like drug discovery and automated labs, and points out future challenges in making AI-driven workflows more reliable and transparent.
Open → 2609.21162v1

MARC predicts consensus maps to improve cell segmentation in spatial transcriptomics

MARC: Morphology-Aware Regression of Consensus for Cell Segmentation in Subcellular Spatial Transcriptomics

Abstract: Accurate cell segmentation remains a major bottleneck in subcellular spatial transcriptomics (SST), in which morphological images and spatially resolved RNA transcripts are used to partition tissues into individual cellular instances. As segmentation serves as the foundation for constructing cell-level representations, boundary errors can lead to incorrect transcript assignments and compromise downstream analyses. However, reliable ground-truth boundaries are unavailable because they must be inferred from incomplete morphological and transcript signals. Furthermore, manual annotation of a large number of cells is time-consuming. Agreement among complementary segmentation methods provides a practical surrogate for identifying well-supported and ambiguous regions, but explicit consensus construction requires executing multiple computationally intensive pipelines. In this study, we propose MARC (Morphology-Aware Regression of Consensus), a framework that predicts a multi-method consensus-support map for SST segmentation. MARC is trained with leave-one-method-out consensus pseudo-targets and a Foreground-Union Consensus Loss that focuses supervision on candidate and consensus foreground. We evaluated MARC on 4,642 held-out tiles from Xenium kidney tissue, achieving a mean Dice score of 0.90, a mean intersection-over-union of 0.82, and a mean cell-level Spearman correlation of 0.79 against explicitly computed cross-method consensus maps. We demonstrate that the predicted consensus maps localise weakly supported regions while preserving consensus-based rankings and identifying low-consensus cells for manual review. These results show that MARC closely approximates explicit cross-method consensus without multi-method inference and therefore has the potential to facilitate robust, consensus-aware evaluation of cell segmentation in large-scale SST studies.

Sat 12 SeptComputer Vision and Pattern Recognition
The gist
Cell segmentation helps scientists identify individual cells in tissue images, which is important for studying cell functions. However, it's hard to get accurate boundaries because the data is incomplete and manual labeling takes too long. The authors developed MARC, a method that predicts consensus maps showing where different segmentation methods agree or disagree. This helps identify uncertain areas without running many complex algorithms, making the process faster and more reliable.
Open → 2609.13665v1