arXiv:2608. 10450v1 Announce Type: cross Abstract: Complex software systems develop over timescales that exceed the lifespan of any individual coding agent.
arXiv:2603. 13428v2 Announce Type: replace-cross Abstract: With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customized software to enable interaction within dynamic environments.
arXiv:2606. 11976v1 Announce Type: cross Abstract: Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue.
E2E-SWE is a benchmark that tests large language models’ ability to create complete, functional software repositories from scratch. It includes 186 tasks across 11 programming languages, each requiring an agent to build an installable project based solely on a natural‑language specification and an empty workspace, while passing a hidden test suite. The benchmark was crafted by software engineers and LLMs, then refined through iterative verification by autonomous agents to ensure clarity and solvability.
Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repositories linearly, that is, visiting one directory or file per step.
arXiv:2606. 24311v1 Announce Type: new Abstract: As large language model (LLM) agents are applied to longer tasks, they increasingly modify workspace state across multiple rounds of iteration.
arXiv:2609.01481v1 Announce Type: new Abstract: This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and u...
arXiv:2606. 00619v1 Announce Type: cross Abstract: Long-horizon autonomous agents require memory systems to retain historical information, track evolving states, and reuse relevant knowledge beyond finite context windows.
arXiv:2603. 13428v3 Announce Type: replace-cross Abstract: Real-world software must continuously evolve to meet ever-changing and open-ended requirements.
The paper introduces Agentic Just-In-Time Software Construction (A-JIT), a paradigm that replaces static software binaries with dynamic systems capable of continuous evolution. In A-JIT, an application consists of code, a runtime harness, and an embedded AI agent that observes usage and execution traces to specialize software logic, workflows, and tool interfaces for each user. This approach enables applications to dynamically generate missing implementations, create new capabilities on the fly, and adapt continuously to end‑user behavior, thereby supporting trace‑driven human‑AI co‑construction and opening a new design space for adaptive, self‑evolving software.
arXiv:2609. 00546v1 Announce Type: cross Abstract: Agent systems are commonly described by the model and harness that currently produce their behavior.
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: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.