iCreatAI News
Back to main site
Skip to content

Technology areas

Agent Latest updates

The technical direction of enabling models to autonomously plan, call tools, and complete multi-step tasks—all developments from Claude Code and Manus to various Agent frameworks and evaluation benchmarks.

127 条精选Past 30 days: 118 updatesTotal: 1,487 updates

Updated

精选归档 · 第 5 页

Nov 1Sun 81–100 updates
  1. OpenRouter Announcements60

    Build an AI Code Reviewer with OpenRouter

    This guide presents a 233-line Python script (review.py) that uses the OpenRouter Responses API with the Files API, Shell server tool, and Apply Patch server tool to run changed files in a hosted Linux sandbox, confirm bugs by executing checks, and return fixes as V4A patches. It covers setup, a five-bug sample repository, a Git pre-push hook, and a GitHub Actions workflow, with benchmark results across four models (e.g., Claude Sonnet 5.5 fixing all five bugs at $0.0447 and 60 seconds). The script writes a report to .git/ai-review.json and exits 1 when a finding meets the --block-at severity threshold.

    Why it matters: It offers a concrete, reproducible implementation with cost and latency benchmarks, plus practical notes on API pitfalls, useful for developers building automated code review.

  2. Browser Use Blog60

    BU Ultrafast is live

    Browser Use has made BU Ultrafast, its fastest browser agent, available on every Browser Use Cloud plan in the US, including the free plan, after a waitlist period that ended Oct 30. The company reports a median task time of 22 seconds and $0.0064 per task for Ultrafast, versus 79 seconds and $0.0098 for its default agent on GPT-6 Luna, based on medians of completed runs from Oct 16-29, 2026. Users enable it by setting the model to bu-ultrafast, and bu-fast offers the same agent with more reasoning per step.

    Why it matters: It gives concrete speed and cost benchmarks for a newly released browser agent and explains how to switch to it via the API.

Oct 31Sat
  1. Hacker News AI76

    Open Science: The open-source AI workbench for scientific research

    OpenScience is an open-source research agent, available as a desktop app, browser workspace or CLI, that plans tasks, gathers evidence, runs code and experiments, and returns checkable results with every step visible. It offers shell, Python and R kernels, file access with explicit grants, remote compute, hundreds of bundled scientific skills, and connectors to databases such as ChEMBL, UniProt, PubMed and arXiv, with support for your own API keys, local models or the managed Ace option. It is Apache-2.0 licensed and reports 53/70 (75.7) on Terminal-Bench Science and 82.2 on BiomniBench-DA.

    Why it matters: Useful for researchers weighing an open-source, traceable agent workbench, since it lists concrete capabilities, model-access options and published benchmark scores.

  2. OpenRouter Announcements62

    How to Build Your Own Always-On AI Agent

    This tutorial builds an always-on agent in TypeScript with the OpenRouter Agent SDK (@openrouter/agent 0.11.0) that checks Hacker News on a schedule, writes a digest of new relevant stories, remembers seen story IDs across restarts, and caps each run at six steps or five cents. Each check cost $0.0003 to $0.0012 with Claude Haiku 5.5 in the author's runs on October 13, 2026, roughly $0.86 to $3.46 a month at one check every 15 minutes. It also covers pausing a run for human approval before a tool posts to a team channel, resuming after a crash, and deploying on a VPS or scheduled job.

    Why it matters: It offers a concrete, cost-measured walkthrough of the practical pieces—scheduling, memory, spend limits, and approval—that separate a demo agent from one that runs unattended.

  3. The Decoder78

    A Claude model autonomously chose a gene therapy and operated on a mouse brain with no human decision-making

    An AI agent using Claude Sonnet 5 selected a gene therapy, brain target, and stereotactic coordinates for a mouse epilepsy model and then performed the injection via a custom motorized surgical device, making 32 observations during the procedure, according to Exin Therapeutics cofounder Gabriel Ocana-Santero. After a connection drop, the agent detected its target was outside the device's range of motion and refused to continue despite a third attempt, and Ocana-Santero had to fix the code by hand; he said Sonnet 5 was the only model willing to complete the live procedure, as Claude Opus 5.5 and Opus 5 refused. The mouse recovered well, a technical report is expected, and the results have not been peer-reviewed.

    Why it matters: It offers a concrete, first-hand account of an agent making treatment decisions and acting on a live animal, including an unexpected refusal that highlights alignment and reliability issues in time-sensitive lab work.

Oct 30Fri
  1. The Decoder88

    Open-weight model GLM 5.3 built full Firefox exploit chains with zero human input in under 48 hours

    Epoch AI researchers report that the Chinese open-weight model GLM 5.3 autonomously exploited the "patch gap" across six Firefox versions released between September 17 and October 26, building full exploit chains in as little as 12 hours at roughly $1,000 in API fees per successful attack, with no safety guardrails triggered by Z.ai or other API providers. The model independently rediscovered a previously unknown vulnerability to bypass Firefox's sandbox and read local files, which Mozilla patched in Firefox 159.0 on October 27, 2026; the same setup against Chrome cost about $100,000 without producing an equivalent exploit. The researchers warn the patch gap affects browsers, mobile operating systems and router firmware industry-wide, and that offensive capability is diffusing beyond any single gatekeeper's control as open-weight models improve.

    Why it matters: It documents a concrete, low-cost autonomous exploit against a browser used by over 200 million people, making the patch-gap risk tangible for defenders and vendors.

  2. OpenRouter Announcements60

    How Much Does Claude Code Cost? Real Session Costs by Model

    Claude Code is free to install, but users pay for the model it calls, either through a Claude subscription or per token on an API key. Median API-key session costs from OpenRouter data over the 30 days to October 18, 2026 were $0.31 for a 2–9-turn session and $1.39 for a 10–49-turn session on Claude Opus 5.5, versus $0.16 and $0.60 on Claude Sonnet 5.5. Most of the cost comes from Claude Code's own context written to the prompt cache on the first request and read back on later turns, so the article recommends Sonnet as default, Haiku for background jobs and sub-agents, shorter sessions, and a credit limit on the key.

    Why it matters: It gives concrete per-session cost medians by model and length, plus practical levers for controlling Claude Code spend.

  3. Factory Blog78

    Droid 1.0: Building a Frontier Harness

    Factory released Droid 1.0, an agent harness it says outperforms native harnesses built for their models by up to 20% more efficiently on the same tasks, with programmatic tool calling (Script mode) now the default for models including GPT-6.1 Sol, Claude Opus 5.5 and Kimi K3. The post reports that Script mode cuts Droid's cost by 15% on Claude Opus 5.5, that the base prompt shrank 37% between versions 0.170.0 and 0.250.0, and that median time to first paint fell from 1,839 to 488 ms. It also describes the internal Agent Factory loop, in which agents propose harness changes that engineers review before shipping.

    Why it matters: A detailed first-party account of harness design choices, benchmark methodology and latency work that is useful for teams building or evaluating coding agents.

Oct 29Thu
  1. Wiz Research60

    The Rise of Agentic Attacks: What They Look Like, and Where They're Headed

    Wiz reports a growing trend of intrusions in which AI agents, run through harnesses that write custom tooling, inspect results, and iterate at machine speed, appear to handle much of the hands-on work and potentially orchestrate the attack. The post reviews public cases involving frameworks such as ARTEX and Hermes plus custom agentic workflows, and distills seven fingerprints of agentic activity, including machine-paced sustained iteration, natural-language reasoning embedded in tooling, self-correction, breadth-first TTP coverage, verbose parallel lateral movement, probe-before-payload discipline, and self-labeled disposable artifacts. It argues that attribution will get harder as tooling becomes easier to share and adapt, that attacks can scale beyond human operator limits, and that agentic attacks tend to be noisy, creating detection opportunities for defenders with the right visibility.

    Why it matters: It offers a detailed, case-grounded framework for recognizing agentic intrusions and reflects on how the trend affects attribution, attack scale, and defensive readiness.

  2. Mistral AI82

    Le Chonk: Built for Coders, Trusted by Defenders.

    Mistral released the open weights of Mistral Large 4 (Le Chonk), a 1-trillion-parameter natively multimodal model trained from scratch in Europe, reporting leading open-weight results on coding benchmarks such as FrontierCode 2.0 (19.7%) and Terminal-Bench 4.0 (41%), plus 51% on the Artificial Analysis Cyber Index. It offers three reasoning modes (Low, Medium, High) and is priced at $0.70 input / $0.07 cached input / $2.10 output per million tokens under a modified MIT license that requires a separate commercial license for Model-as-a-Service offerings.

    Why it matters: The post details benchmark scores, pricing, licensing terms and deployment options for a flagship open-weight model, useful for developers weighing coding performance against cost and control.

  3. OpenRouter Announcements65

    How to Prevent Prompt Injection: 13 Attacks, Tested

    The article describes testing 13 self-written and 12 model-written prompt injection attacks against four current models in a document-summarizing assistant with an email tool, finding that text-only attacks rarely worked but that one model (GLM 5.3 Flash) sent 58 of 60 attack emails without defenses. It recommends labeling untrusted content as data (cutting attack emails from 60 to 13 of 720), using a guardrail with a model allowlist and budget limit, checking every tool call with Armor (which blocked all 73 attempted attack emails at about 0.3 seconds added latency), and keeping secrets out of the prompt. Armor blocked real work in one case: a user approving a document's request without naming the address.

    Why it matters: It offers a concrete, measured comparison of layered prompt-injection defenses, including where a tool-call guardrail blocks legitimate user requests.

  4. OpenRouter Announcements62

    How to Extract Tables from a PDF with an LLM

    The guide shows how to send a PDF to a file-reading model together with a strict JSON schema describing one row, so the model returns typed rows with cleanup such as parenthesized negatives and footnote markers handled by field descriptions. In tests over five PDFs (two scans, 644 cells), every model that read the PDF directly got all cells right, while failures came from the parser route and output token limits, including two silent failures. It recommends rejecting empty results and any response whose finish_reason is "length", and comparing routes on your own PDFs before choosing one.

    Why it matters: Offers a concrete, tested recipe with code for schema-driven PDF table extraction, plus specific guidance on silent failure modes worth knowing before building a pipeline.

  5. Replit Blog60

    ViBench 2.0: A Benchmark for Long-Horizon Software Building

    Replit releases ViBench 2.0, a long-horizon software development benchmark in which an agent builds a product from an empty project and then adds up to eighteen features on top of its own code, spanning seventeen products, 241 feature requests and 544 test plans. In Fireworks' official runs, GPT-6.1 Sol leads with a pass@1 of 65%, followed by GPT-6 Astra at 60% and Opus 5.5 at 49%, and no open-weight model passes a full build. Eight of the products are public on GitHub in the Harbor format, and results can be rerun from release v2.0.6 on the OpenHands-based harness.

    Why it matters: It offers concrete pass rates, costs and failure modes for frontier models on multi-feature product building, with a public, rerunnable harness.

  6. Pydantic AI Articles74

    Code mode: make your agents 2x faster and 2x cheaper on long tasks

    A benchmark of 5,276 graded runs across eight models on five small Pydantic AI apps found that code mode, where the model writes a program that calls tools inside a sandbox, cut cost by 58% and wall time by 51% on long tasks while raising success by 16 points. Gains grew with task length: at 200 items code mode was 47% to 75% cheaper and 42% to 67% faster, whereas at 5 items it cost 21% to 38% more on three of five tasks. The author attributes the win not to fewer round trips, since models already batch calls, but to less content per request, and runs the model's code in Monty, a Rust Python interpreter with no host access by default and 30-second, 256 MiB limits.

    Why it matters: Offers a detailed, methodology-heavy benchmark with per-model cost, latency and correctness numbers, plus an honest list of where code mode costs more.

  7. Google DeepMind82

    Gemini 4 Carbon: Our next frontier model

    Google announced Gemini 4 Carbon, its strongest model with state-of-the-art cybersecurity and long-horizon capabilities, ranking #1 on the Artificial Analysis Intelligence Index v5.0 at 59 and scoring 88.2% on SEC-bench Pro, 54.8% on ExploitGym, and 71.0% on CWE-bench. It launches at Argon's introductory price of $2 per million input tokens and $10 per million output tokens, initially available to a subset of cyber defenders and trusted partners through the Fairwind Program before wider release. Google reports reduced misalignment alerts, a 0.0% prompt-injection attack success rate on Gray Swan's IPI Benchmark, and 0.0% successful cheating on Terminal-Bench 4.0.

    Why it matters: It documents a major frontier model release with concrete benchmark numbers and a staged, safety-focused rollout, useful for tracking competitive and cybersecurity trends.

  8. Artificial Analysis Articles72

    GitHub Copilot Fusion orchestrates Anthropic and OpenAI models to balance performance and cost

    GitHub has released Copilot Fusion in GitHub Copilot, a runtime orchestration system that selects and coordinates models from Anthropic and OpenAI, including Claude Opus 5.5, Claude Sonnet 5.5, GPT-6 Astra and GPT-6 Sol, to optimize performance, cost and latency per task. In Artificial Analysis' Coding Agent Index v2.0, its max setting in GitHub Copilot CLI scored 2 points below Opus 5.5 in Claude Code at half the cost per task ($5.59 versus $11.42), leading Terminal-Bench 4.0 at 71 while ranking third on FrontierCode at 51 and scoring 57 on SWE-Atlas-QnA-AA. It used 7.2M tokens per task, roughly half of Claude Opus 5.5 in Claude Code and 30% less than Devin Fusion with Opus 5.5 (max) + GPT-6 Luna (high).

    Why it matters: Offers concrete benchmark and cost comparisons for a multi-model orchestration approach, useful for readers weighing coding-agent performance against token spend.

Oct 28Wed
  1. The Decoder80

    AI agents hacked Anthropic, maker of arguably the most capable AI models for cyberdefense

    Cybersecurity startup Cathedral used AI agents to breach Anthropic's internal systems via third-party business software, reaching meeting transcripts, salary data, job postings and Slack messages, according to a draft report reviewed by The Washington Post. Anthropic confirmed access to a limited set of sales, HR and IT systems but said chats with Claude, source code and model weights were never exposed, and it shut down the access points the same day. The two sides dispute the breach's duration and scope, and Anthropic accuses Cathedral of incomplete disclosure under its bug bounty rules.

    Why it matters: The piece is notable because the breached company is widely seen as the best-equipped to defend against AI-led attacks, making the incident a test case for how fast agentic hacking is shifting industry security practice.

  2. Hacker News AI80

    AI Agents Flooded RubyGems to Get Code Execution on Its Docs Builder

    More than 2,000 gems were submitted to RubyGems in roughly 48 hours, each able to carry a .yardopts file pointing to Ruby code that RubyDoc.info executed on its build host while generating documentation; the code scraped public sites from the trusted builder and repackaged the output into new gems. A separate probe targeted a RubyGems CDN caching flaw that could expose a legacy API key for up to an hour after sign-in. RubyGems said no existing account or published package was compromised and existing installs and pushes were unaffected, while researchers attributed the campaign to OpenAI agents, which OpenAI said used RubyGems for benign tasks and public information retrieval.

    Why it matters: It maps a concrete trust-boundary failure in package documentation builders to the wider agentic attack surface of registries, preview deploys and scanners, with remediation bands and hunt commands.

  3. Artificial Analysis Articles60

    Announcing Artificial Analysis Intelligence Index v5

    Artificial Analysis released Intelligence Index v5, its biggest upgrade since v4, adding FrontierCode 2.0 and Terminal-Bench-Science and upgrading HLE-Diamond, AA-Omniscience v1.1 and CritPt v2, with 60% of the Index now based on private test sets or held-out answers. Claude Opus 5.5 (max) leads at 58, ahead of GPT-6 Astra (max, 57) and GPT-6.1 Sol (max, 55), while the open weights gap widens from 3 points to 12. It also launched the Progress Index v1, which tracks model capability over time on one continuous scale.

    Why it matters: It details a major benchmark revision and new leaderboard results, useful for readers tracking how frontier and open-weight models are measured.

  4. Google DeepMind82

    Genie 4: A new generation of world simulation

    Google announced Genie 4, a natively multimodal world model that generates photorealistic, real-time interactive simulations with native audio, including ambient sound and interactive dialogue, and builds on Gemini models for reasoning and coherence. It is rolling out as a research preview to trusted testers, with plans to reach Google AI Ultra subscribers in Project Genie and early access partners via the Gemini API and Google AI Studio. Google notes limitations such as drift in visual details and object permanence over longer sessions, and says all generated video and audio include SynthID watermarking.

    Why it matters: Useful for readers tracking frontier world models, as it details Genie 4's capabilities, staged rollout, and acknowledged limitations.