Skip to content
Live
Official sources#Open source
Apr 14Tue
  1. Moonshot AI · Hugging Face new models

    Kimi K2.6 released: Open-source multimodal agent model breaks performance in long-term encoding and autonomous execution

    Kimi K2.6 is an open-source multimodal intelligent agent model that has made significant progress in long-term encoding, encoding-driven design, proactive autonomous execution, and group task orchestration. It has 1 trillion parameters, a context length of up to 256k tokens, achieving a score of 54.0 on the HLE-Full benchmark and 86.3 on the BrowseComp (agent group) benchmark, and supports 300 sub-agents executing 4,000 coordinated steps in parallel.

Apr 10Fri
  1. LangChain Blog

    Deep Agents Deploy: An open-source alternative for deploying intelligent agents, replacing Claude Managed Agents.

    Deep Agents Deploy Officially Released as an Open Source Alternative to Claude Managed Agents for Intelligent Agent Deployment, Supporting Any LLM Model, Achieving Model-Agnostic, Production-Ready Deployment via the `deepagents deploy` Command, Users Can Customize AGENTS.md Instruction Sets and Agent Skills, and Choose a Sandbox Environment to Ensure Memory Ownership is Not Locked.

Apr 3Fri
Apr 2Thu
Mar 17Tue
Mar 13Fri
  1. Berkeley AI Research

    How do SPEX and ProxySPEX algorithms scale to identify LLM interactions

    The SPEX algorithm identifies key interactions of LLMs through signal processing and coding theory, analyzing the impact of features, data, and model components with only a small amount of disturbance, achieving high fidelity in sentiment analysis tasks even with thousands of features; The ProxySPEX algorithm leverages model hierarchical structure characteristics, reducing the number of disturbances by 10 times while maintaining performance.

Feb 23Mon
  1. Anthropic Research58

    Anthropic proposes a role selection model to explain AI human-like behavior

    Anthropic proposed a persona selection model to explain AI's human-like behavior, suggesting that large language models learn personas from text during pre-training and adjust rather than change their essence during post-training. This model can explain Claude's anti-Alignment behavior when trained to cheat, implying that developers need to focus on the psychological aspects of the personas behind the behavior rather than just judging the behavior itself, and recommending the introduction of more positive AI role models.

Feb 18Wed
Jan 29Thu
  1. LangChain Blog

    How does the LangChain Deep Agents SDK implement efficient context management?

    The LangChain Deep Agents SDK manages limited memory of AI agents through three compression techniques: offloading large tool results (>20,000 tokens) and inputs (>85% context window) to the file system, and using LLM to generate session summaries. The SDK triggers compression on Claude Sonnet 4.5 in terminal benchmark tests, retaining complete records through filesystem search and summaries, supporting frequent compression to optimize performance.

Jan 15Thu
  1. Anthropic Research50

    How scientists use Claude to accelerate research and discovery

    Scientists have achieved significant progress in biological illustration, computational biology, and protein understanding benchmarks using Claude 4.5, a model now available to top researchers worldwide via API for free, and has built custom systems that go beyond literature reviews or coding assistance. In the lab, Claude serves as a collaborative partner throughout the research process, compressing projects that usually take months into hours using various tools, and discovering large-scale data patterns that humans might overlook, eliminating bottlenecks in knowledge-intensive tasks, and even enabling entirely new research approaches that traditional methods cannot adopt.

Jan 14Wed
  1. Anthropic Research67

    Anthropic uses Claude with property testing to find bugs in the Python ecosystem

    Anthropic's research team developed an agent based on Claude Code custom commands, which infers the properties that code should satisfy by reading type annotations, docstrings, and comments, and then uses Hypothesis to write property tests, discovering hundreds of potential bugs in over 100 popular Python packages such as NumPy, SciPy, and Pandas.

    Why it matters: Anthropic uses Claude agents to automatically write property tests to find bugs in packages like NumPy, SciPy, Pandas, and provides the efficiency after manual review and merged fixes

Jan 10Sat
  1. Berkeley AI Research

    Berkeley AI research proposes an information-driven imaging system design framework

    Berkeley AI research proposes an information-driven imaging system design framework, which quantifies the object's discrimination capability through mutual information measurement. It has been validated in four fields: color photography, radio astronomy, lensless imaging, and microscopy that information estimation can predict decoder performance. The optimized mutual information design scheme achieves end-to-end optimal results while reducing memory and computational load.

Jan 8Thu
  1. Anthropic Research58

    Anthropic Collaborates with PNNL to Simulate Attacks with Claude to Defend Critical Infrastructure

    Anthropic partnered with the Pacific Northwest National Laboratory (PNNL) to use the Claude model to quickly simulate network attacks in a simulated water treatment plant network, proving that AI can accelerate defense drills, completing attack reconstruction in just three hours instead of weeks; Claude Sonnet 4 demonstrated resourcefulness in testing by bypassing the Windows UAC security feature through predefined tools and identifying alternative techniques to achieve the goal.

Dec 18Thu
Nov 12Wed
  1. Anthropic Research

    Project Fetch: Can Claude Train a Robot Dog?

    Eight Anthropic researchers (with no robotics experience) were randomly divided into two groups, one using Claude and the other not, tasked with using quadruped robot dogs to pick up beach balls. The team using Claude completed more tasks faster and was the only one to achieve the goal of making the robot completely autonomous in picking up the balls. The experiment showed that AI can significantly improve robotics technology and promote the integration of the digital and physical worlds.

Oct 6Mon
  1. Anthropic Research71

    Anthropic open-sources security audit tool Petri

    Anthropic has released an open-source auditing tool, Petri (Parallel Exploration Tool for Risky Interactions), where automated agents test target models through multi-round dialogues, and then LLM reviewers score them based on safety dimensions and select the most worthy dialogues for manual review.

    Why it matters: Anthropic has open-sourced the automated auditing tool Petri and provided cross-comparison results for 14 cutting-edge models on behaviors such as deception, sycophancy, and self-preservation.

Nov 14Thu
  1. LangChain Blog

    Promptim: An experimental library for prompt optimization

    Promptim is an experimental prompt optimization library that automatically runs an optimization loop to generate better prompts by providing an initial prompt, a dataset, and a custom evaluator (optional human feedback). It integrates LangSmith for dataset management, prompt management, and result tracking (optional human annotation). The core algorithm modifies prompts based on evaluator feedback and iteratively optimizes, supporting human feedback loops. The tool aims to save manual prompt engineering time, introduce rigorous processes, and simplify model switching, but requires manual review.