arXiv AI
Jun 12
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
arXiv:2606. 13662v1 Announce Type: new Abstract: LLM-based agents have shown increasing potential in automating scientific discovery.
Can AI Scientists Coordinate at Runtime?
Related stories
arXiv AI
Jul 29
OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simulation
arXiv:2607. 25656v1 Announce Type: new Abstract: Complex tasks often decompose into parallelizable yet interdependent subtasks, making orchestration critical to the performance of multi-agent systems (MAS).
arXiv AI
Sep 15
OpenAl4S: Code as Action, Science as Sessions
OpenAI4S is an open‑source scientific research agent that treats code as action and science as sessions, combining a persistent computing runtime with structured session management. It uses tool calls for orchestration, executes code cells in persistent Python and R kernels, and records an append‑only Action Ledger, per‑cell execution logs, versioned artifacts, environment snapshots, and workspace checkpoints to preserve provenance and enable session recovery, branching, and extension. Evaluated on 36 research scenarios—including retrosynthesis, molecular dynamics, and protein design—OpenAI4S achieved a higher overall score (7.83) than a general‑purpose coding harness, especially on long‑horizon, computation‑intensive workflows, though reproducibility remains an open challenge. whyItMatters":"The system demonstrates that persistent execution coupled with session‑level provenance can enhance the reliability of AI‑assisted scientific workflows, as evidenced by its superior performance across diverse research scenarios."
arXiv AI
Aug 12
DSAgentBench: Can Agents Automate End-to-End Data-Science Workflows in Real Computer Environments?
arXiv:2608. 10366v1 Announce Type: new Abstract: Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coordinated use of tools such as notebooks, IDEs, terminals, browsers, and databases within real operating environments.
arXiv AI
Sep 2
Dr. Claw: An AI Scientist Workspace for Vibe Research
Dr. Claw is an open‑source AI scientist workspace that integrates existing command‑line coding agents into a single, auditable, human‑in‑the‑loop workflow. It uses persistent state objects, a reusable skill library, and multi‑executor coordination to link human decisions with AI execution, creating a traceable and recoverable loop for planning, execution, and writing. The authors demonstrate the system with an interactive scenario and a failure‑recovery walkthrough, and show that, when the underlying executor is held constant, Dr. Claw achieves higher research completeness while preserving an auditable process trail.
arXiv AI
3d ago
OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
OpenCollab is a multi‑agent coding framework that unifies organization design, enforces experimental control on a shared runtime, and tracks execution via fine‑grained event streams. It introduces the metric Adherence to measure whether the declared organization is actually realized, showing that small configuration changes can shift adherence from 47.2% to 97.2%. Experiments demonstrate that a two‑coder workflow built on OpenCollab achieves new state‑of‑the‑art performance against mainstream harnesses while using the fewest tokens, and that a well‑designed organization can outperform strong existing harnesses.
arXiv AI
Jul 9
Effective Strategies for Asynchronous Software Engineering Agents
arXiv:2603. 21489v2 Announce Type: replace-cross Abstract: AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github.
arXiv AI
Jun 9
SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?
arXiv:2606. 07682v1 Announce Type: cross Abstract: AI agents are increasingly expected to complete long-horizon workflows that require sustained progress over hours, millions of tokens, and complex environments.
arXiv AI
Aug 7
Hierarchical Server Architecture for Agentic Science
arXiv:2608. 05332v1 Announce Type: cross Abstract: Agentic science is transforming the landscape of computational work, extending to scientific pipelines and workload managers.
arXiv AI
Jun 11
Engineering Robustness into Personal Agents with the AI Workflow Store
arXiv:2605. 10907v3 Announce Type: replace-cross Abstract: The dominant paradigm for AI agents is an "on-the-fly" loop in which agents synthesize plans and execute actions within seconds or minutes in response to user prompts.
arXiv AI
Aug 28
DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows
DuMateBench is a new benchmark for autonomous agents that uses real user sessions from a large production platform, preserving interaction history, configurations, and workspace state. It contains 200 tasks across 8 scenarios and 17 capability categories, many requiring coordination of multiple capabilities. The benchmark tests agents in Docker containers with real-world complexities—Insufficient, Unstable, and Noisy—and evaluates performance with a hybrid deterministic and LLM-as-Judge protocol, revealing significant gaps in task completion across various agent frameworks and LLMs.
arXiv AI
Sep 23
APEXA: Execution-Integrity Enforcement for Multi-Agent LLM Automation of Synchrotron Data Reduction
arXiv:2609.24165v1 Announce Type: new Abstract: Synchrotron data reduction, detector calibration followed by azimuthal integration of terabyte-scale diffraction series, is a multi-step, expert-bound...