@seclink: Another open-source sample... Normally, you'd have to pay for this, but that said, since it's open-sourced, it's defini…
Summary
This post announces Autoresearch Bench, an open-source benchmark for coding agents to autonomously tackle research problems, noting stark differences between models in autoresearch loops.
View Cached Full Text
Cached at: 09/03/26, 12:05 PM
Another open-source sample… Normally, you’d have to pay for this, but that said, since it’s open-sourced, it’s definitely one of those things that aren’t particularly valuable in hand, so they release it as open source.
Joseph Wang (@potatodonkey): Announcing Autoresearch Bench
A benchmark for coding agents autonomously tackling research problems
While existing coding benchmarks are saturating quickly, the difference between models in autoresearch loops is stark
Similar Articles
@VukRosic99: A DeepSeek researcher just open-sourced his AutoResearch personal project. For the first time, the AutoResearch Agent a…
A DeepSeek researcher open-sourced AutoResearch, an autonomous framework that can plan, execute, and debug RL experiments on the DeepSeek 285B model without human intervention, accompanied by a self-play survey paper.
@Lyubh22: Coding benchmarks are saturating. AI4Research is the next frontier. Thrilled to see our MLS-Bench (https://mls-bench.co…
Announcing MLS-Bench, the first AI4Research benchmark to gain broad community adoption, testing AI agents on 140 executable tasks across 12 domains to propose modular ML improvements. The post includes leaderboard scores for models like Claude Opus 4.6 and GPT-5.4.
@KaiZhang_CS: Check out one of the best open-source search agents trained by @jianxie_ !! glad to see early experience methods work o…
Yu Su's team trained a frontier Deep Research Agent on an academic budget using 8K synthetic samples and RL, releasing fully open training infrastructure and models from 2B to 35B parameters.
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
ResearchClawBench is a benchmark for evaluating end-to-end autonomous scientific research across 40 tasks from 10 domains, revealing that current AI agents and LLMs achieve low re-discovery accuracy, with Claude Code averaging 21.5 and Claude-Opus-4.7 averaging 20.7 out of a possible score.
@lftherios: 1/ Autoresearch from @karpathy has been one of the most interesting agentic patterns to emerge this year. The challenge…
Andrej Karpathy's autoresearch pattern highlights how current AI agents run experiments in isolation, wasting compute by duplicating work and rediscovering dead ends.