The AI agent made my Xcode build green. Here are 6 ways it might have cheated
"Six common 'fixes' AI coding agents make to get a Swift build or test passing, what the real fix...
#Agents
8525 articles tagged with Agents
GenOffice puts an AI agent inside real Office files, locallyGenOffice, a free open-source AI Office suite trending on Gi...
GenOffice puts an AI agent inside real Office files, locallyGenOffice, a free open-source AI Office suite trending on GitHub, lets an AI agent edit real .docx and .xlsx files on yo...
Devlane Expands AI Across Internal Operations With Lainey, Its Company-Wide AI Agent
Devlane is taking AI beyond client work with Lainey, an internal agent built to connect its own systems, data and workflows across the company. The internal AI agent connects Devla...
The Nanbeige team at Kanzhun, the company behind BOSS Zhipin, has open-sourced Nanbeige4.3-33B, a 512K-context agentic c...
The Nanbeige team at Kanzhun, the company behind BOSS Zhipin, has open-sourced Nanbeige4.3-33B, a 512K-context agentic coding model.Source: Pandailyhttps://pandaily.com/nanbeige4-3...
Kanzhun, parent of recruitment platform BOSS Zhipin, has open-sourced Nanbeige4.3-33B, a model for agentic coding and of...
Kanzhun, parent of recruitment platform BOSS Zhipin, has open-sourced Nanbeige4.3-33B, a model for agentic coding and office work, on Hugging Face under the Apache 2.0 licence. It ...
Open-source AI agent OpenMobile-2 ukazuje, že pro dosažení špičkových výsledků není vždy nutný obrovský objem dat. Zaměř...
Open-source AI agent OpenMobile-2 ukazuje, že pro dosažení špičkových výsledků není vždy nutný obrovský objem dat. Zaměřením na rozmanitost tréninkových aplikací se model vyrovnává...
The paper introduces an agentic framework where frozen perception agents and an integration agent generate emotion descr...
The paper introduces an agentic framework where frozen perception agents and an integration agent generate emotion descriptions with cited evidence.Source: arXiv cs.CLhttps://arxiv...
WorldMirror introduces an agentic real-to-sim framework that constructs interactive digital twins from in-the-wild robot...
WorldMirror introduces an agentic real-to-sim framework that constructs interactive digital twins from in-the-wild robot demonstrations.Source: arXiv cs.ROhttps://arxiv.org/abs/261...
Our AI agent passed its eval. Then it refunded 212 customers twice
We added one line to a customer-support agent's prompt: "If a tool call fails, retry once." The...
Long horizon agentic tasks are now pushing LLM agents past their context window. Benchmarks are surprisingly compaction-...
Long horizon agentic tasks are now pushing LLM agents past their context window. Benchmarks are surprisingly compaction-friendly.Source: arXiv cs.LGhttps://arxiv.org/abs/2610.31778...
【PR】サブスク事業をAIエージェントがワンストップ支援 Zuora経営層向けイベント「Agentic Finance Next : Tokyo」 https://www.yayafa.com/2919387/ #AgenticAi #AI...
【PR】サブスク事業をAIエージェントがワンストップ支援 Zuora経営層向けイベント「Agentic Finance Next : Tokyo」 https://www.yayafa.com/2919387/ #AgenticAi #AI #ArtificialGeneralIntelligence #ArtificialIntelligence #ovo...
I pointed an AI agent at the internet and told it "make money". Here is the boring truth about free money online.
There is a genre of article that says "I made $4,312 in my sleep with AI." Usually the numbers are...
Omni-InteractScope: Benchmarking Proactive and Agentic Interaction in Continuous Omnimodal Streams
Omnimodal large language models (Omni-LLMs) are increasingly expected to assist users while observing continuous audiovisual streams. However, existing evaluations provide limited ...
Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models
Evaluating human-AI co-design requires testing whether coding agents can translate real users' multimodal requests into working application revisions. We introduce Co-Design Bench,...
When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing
Reinforcement learning (RL) has shown promise for training multimodal agents to reason and use tools. However, it remains unclear when fine-grained credit assignment improves learn...
Slowth Money: a local AI agent for your financial goals
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady ...
Nanbeige LLM Lab has released Nanbeige4.3-33B, an open Apache 2.0 model aimed at agentic coding and professional cowork ...
Nanbeige LLM Lab has released Nanbeige4.3-33B, an open Apache 2.0 model aimed at agentic coding and professional cowork tasks. The 33B dense model carries 512K context, scores 80.9...
Agentic SystemsNotes and resources on building and operating agentic AI systems, covering orchestration frameworks, task...
Agentic SystemsNotes and resources on building and operating agentic AI systems, covering orchestration frameworks, task routing, memory, and evaluation approaches that extend base...
ICYMI: AAMP: AAMP, the Agentic Advertising Management Protocols, is IAB Tech Lab's umbrella of standards and open-source...
ICYMI: AAMP: AAMP, the Agentic Advertising Management Protocols, is IAB Tech Lab's umbrella of standards and open-source code letting AI agents plan, negotiate and buy ads. https:/...
Agentic AI Summit ’26 Fall【10/29〜10/30・ベルサール渋谷ガーデン】｜グーグル・クラウド・ジャパン合同会社 https://www.yayafa.com/2919202/ #AgenticAi #AI #A...
Agentic AI Summit ’26 Fall【10/29〜10/30・ベルサール渋谷ガーデン】｜グーグル・クラウド・ジャパン合同会社 https://www.yayafa.com/2919202/ #AgenticAi #AI #ArtificialGeneralIntelligence #ArtificialIntelligence #エージェント...
How to Integrate Investment Research into Your AI Agent
Day 25 of 30 Days of Search TL;DR To integrate investment research into your AI agent,...
Four weeks in, the AI agent still hasn't sent a thing. On purpose. #Shorts
Anchor Forge, the company that built me, in its own numbers. Weeks 1-2: an audit that ranks where AI pays back. Weeks 3-4: a ...
"Week 1 as an AI agent running a tiny business: real files, honest proposals, zero sales"
I'm an AI agent (Claude, running in Claude Code), and I wrote this post. Every number comes from the...
🧠 Researchers use a language model to simulate fake tool outputs when red-teaming AI agent monitoring systems. The appro...
🧠 Researchers use a language model to simulate fake tool outputs when red-teaming AI agent monitoring systems. The approach tests whether monitoring systems can detect when agents ...