Paper2Agent is an automated framework that converts research papers and their associated code, data and workflows into interactive AI agents, effectively turning static manuscripts into virtual corresponding authors. The system extracts a paper’s key contributions with multiple helper agents, packages executable functions, static resources and structured workflow prompts into a Model Context Protocol (MCP) server, and wraps that server with LLM-based agents for natural-language interaction and autonomous execution. Users can ask complex scientific questions or request analyses without installing environments or parsing APIs: MCP tools run validated code, MCP resources expose manuscripts and datasets, and MCP prompts orchestrate reproducible multi-step workflows. Demonstrations include agents that reproduce and extend results from AlphaGenome, Scanpy and TISSUE, and a multi-agent collaboration that prioritized a causal gene for psoriasis.
The framework emphasizes reliability and reproducibility by validating tools against reported figures and example datasets, locking tested tool implementations, and including explicit code references to prevent “code hallucination” and limit randomness in code generation. Building on MCP as an industry interface, Paper2Agent generalizes prior executable-paper and containerization efforts by agentifying full research outputs so methods can be applied, adapted and composed via dialogue. This reframes scientific dissemination from static documents to interactive, interoperable AI co‑scientists that lower technical barriers and accelerate reuse.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
OpenJev allows users to run decision models directly in their browser using local models like MiniCPM5 2B or Qwen3 0.6B, without needing a backend. It compares two methods: reading option probabilities directly or generating them token by token, with all data staying on the user's device. (openjev.com)
LLM watermarking, such as Anthropic's invisible watermark based on Google DeepMind's SynthID-Text, is becoming regulated under the EU AI Act for provenance and authenticity. Watermarking can alter AI model and agent behavior, impacting safety features like refusal of harmful requests and robustness against prompt injection. (lasso.security)
Waymo has launched autonomous vehicle services in Singapore. The company is still in the early stages of deployment, with initial visuals reflecting North American driving conditions. (waymo.com)
Orbital is an open source project that provides an open source version of the Claude AI model, allowing users to retain ownership of their data and context. It aims to offer an alternative to proprietary AI models with transparency and control. (github.com)
ShapeLearn's full models for Qwen 3.8 27B outperform the Lite versions in quality and speed benchmarks, with all five models on the performance frontier. Using GPU-5, these models achieve up to 99.63% of BF16 scores, with options for faster, smaller models depending on memory constraints. (byteshape.com)
Claude Code from Source details the architecture and design of Anthropic's widely used AI coding agent, covering components like the agent loop, tool execution, and memory management. The book provides technical insights for engineers, leaders, and anyone interested in production AI systems. (claude-code-from-source.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.