Search Results for "test"

...GPT-4) into software engineering agents that can resolve issues in real GitHub repositories. On the SWE-bench, the SWE-agent resolves 12.47% of issues, achieving state-of-the-art performance on the full test set. We accomplish our results by designing simple LM-centric commands and feedback formats to make it easier for the LM to browse the repository, and view, edit, and execute code files. We call this an Agent-Computer Interface (ACI).

Industry-leading developer platform to test and debug AI agents. We built the tools so you don't have to. Visually track events such as LLM calls, tools, and multi-agent interactions. Rewind and replay agent runs with point-in-time precision. Keep a full data trail of logs, errors, and prompt injection attacks from prototype to production. Native integrations with the top agent frameworks.

The project is the codebase for an AI agent named Cicero developed by Facebook Research. It is designed to play the board game Diplomacy by combining open-domain natural language negotiation with strategic planning. The repository includes training code, model checkpoints, and infrastructure for both language modelling (via the ParlAI framework) and reinforcement learning for strategy agents. It supports two variants: Cicero (which handles full “press” negotiation) and Diplodocus (a variant...

AgentEX is an open framework from Scale for building, running, and evaluating agentic workflows, with an emphasis on reproducibility and measurable outcomes rather than ad-hoc demos. It treats an “agent” as a composition of a policy (the LLM), tools, memory, and an execution runtime so you can test the whole loop, not just prompting. The repo focuses on structured experiments: standardized tasks, canonical tool interfaces, and logs that make it possible to compare models, prompts, and tool sets fairly. It also includes evaluation harnesses that capture success criteria and partial credit, plus traces you can inspect to understand where reasoning or tool use failed. ...

Mini-Agent is a minimal yet production-minded demo project that shows how to build a serious command-line AI agent around the MiniMax-M2 model. It is designed both as a reference implementation and as a usable agent, demonstrating a full execution loop that includes planning, tool calls, and iterative refinement. The project exposes an Anthropic-compatible API interface and fully supports interleaved thinking, letting the agent alternate between reasoning steps and tool invocations during...

...This Data Analysis Agent effortlessly automates all the tasks such as data cleaning, preprocessing, and even complex operations like identifying target objects, partitioning test sets, and selecting the best-fit models based on your data. With Streamline Analyst, results visualization and evaluation become seamless.

Petri is an open-source alignment auditing agent that lets researchers rapidly test concrete safety hypotheses against target models using realistic, multi-turn scenarios. Instead of building bespoke evals, Petri automatically generates audit environments from seed “special instructions,” orchestrates an auditor model to probe a target model, and simulates tool use and rollbacks to surface risky behaviors. Each interaction transcript is then scored by a judge model using a consistent rubric so results are comparable across runs and models. ...