<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>ai-research</title>
    <link rel="self" type="application/atom+xml" href="https://links.biapy.com/guest/tags/3473/feed"/>
    <updated>2026-08-12T15:46:48+00:00</updated>
    <id>https://links.biapy.com/guest/tags/3473/feed</id>
            <entry>
            <id>https://links.biapy.com/links/13594</id>
            <title type="text"><![CDATA[Prime Agent]]></title>
            <link rel="alternate" href="https://github.com/PrimeIntellect-ai/prime-agent" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13594"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Prime Agent is an open-source coding and research agent for general and long-running work.]]>
            </summary>
            <updated>2026-08-10T12:40:30+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13496</id>
            <title type="text"><![CDATA[OpenResearcher]]></title>
            <link rel="alternate" href="https://github.com/TIGER-AI-Lab/OpenResearcher" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13496"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis.

OpenResearcher is a fully open agentic large language model (30B-A3B) designed for long-horizon deep research scenarios. It achieves an impressive 54.8% accuracy on BrowseComp-Plus, surpassing performance of GPT-4.1, Claude-Opus-4, Gemini-2.5-Pro, DeepSeek-R1 and Tongyi-DeepResearch. We fully open-source the training and evaluation recipe—including data, model, training methodology, and evaluation framework for everyone to progress deep research.]]>
            </summary>
            <updated>2026-08-03T06:49:53+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13495</id>
            <title type="text"><![CDATA[Hyperresearch]]></title>
            <link rel="alternate" href="https://github.com/jordan-gibbs/hyperresearch" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13495"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Agent-driven research knowledge base. Agents collect, search, and synthesize web research into a persistent, searchable wiki.

Hyperresearch turns Claude Code into a deep research agent: one that currently leads the DeepResearch-Bench RACE leaderboard (benchmarked internally). A tier-adaptive 16-step pipeline takes one prompt and produces an adversarially-audited report with full source provenance. Every source it reads lands in a persistent, searchable vault, so each session starts smarter than the last.]]>
            </summary>
            <updated>2026-08-03T06:49:06+00:00</updated>
        </entry>
            <entry>
            <id>https://links.biapy.com/links/13094</id>
            <title type="text"><![CDATA[🔬 Scholar Loop]]></title>
            <link rel="alternate" href="https://github.com/renee-jia/scholar-loop" />
            <link rel="via" type="application/atom+xml" href="https://links.biapy.com/links/13094"/>
            <author>
                <name><![CDATA[Biapy]]></name>
            </author>
            <summary type="text">
                <![CDATA[Autonomous, multi-agent AI research — a PhD&amp;#039;s workflow on a single-GPU budget.

 An autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with deterministic guards against reward-hacking and hallucination. 

ScholarLoop runs the loop a PhD actually runs: it reads the literature, forms a grounded hypothesis, runs real ML experiments, scores them against a frozen ground-truth metric, learns from its failures, and drafts a peer-reviewed write-up — autonomously, with a deterministic harness that keeps the agents honest and impossible to reward-hack.]]>
            </summary>
            <updated>2026-06-23T06:24:51+00:00</updated>
        </entry>
    </feed>
