60 stories tagged with #agent, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Agent"
Cq: A Shared Knowledge Commons for AI Agents
Programming book reviews, programming tutorials,programming news, C#, Ruby, Python,C, C++, PHP, Visual Basic, Computer book reviews, computer history, programming history, joomla, …
LM Studio Bionic: the AI agent for open models
The AI agent made for open models, built to get things done.…
Veta: AI agent that QA-tests Android apps
Autonomous AI agent swarm for visual, functional, and accessibility testing of Android apps and mobile web - powered by vision-capable AI models and containerized Android instances…
Working with Pi Coding Agents
The most interesting thing about Pi isn't any single feature; it's that the project treats "what we didn't build" as documentation worth writing, which is rare enough on its own to…
Show HN: AgentReady – MCP server that makes any docs site queryable by AI agents
Paste a URL and get a spec-compliant llms.txt generator plus live /ask and MCP endpoints in 60 seconds.…
Show HN: Termaxa – I found my AI-agent gate had silently stopped gating Cursor
A cooperative gate for the shell commands AI agents run. Previews, backups, policy, audit. Claude Code + Cursor. A windshield, not a sandbox. - termaxa/termaxa…
AI agents write PostgreSQL like Python
Field notes from a production review of an AI-written PostgreSQL backend: exception blocks as control flow, casts that turn bad requests into 500s, races on state-advancing updates…
Rethinking Databases for Humans and AI Agents
Databases Were Built for Engines. It’s Time to Build Them for Humans.…
Semantic transactions: securing untrusted AI agent workflows at the OS boundary
Trust the system, not the prompt: Securing untrusted LLM tools with transactional boundaries and effect outboxes.…
OpenAI launches a $230 physical control panel for managing Codex agents - Neowin
OpenAI launches a $230 physical control panel for managing Codex agents Neowin…
I created OpenClaw, the breakthrough AI agent [video]
OpenClaw creator Peter Steinberger takes us back to the transformative moment he let his AI agent loose on the internet, igniting one of the world's fastest-growing open-source pro…
OpenAI Codex Micro Ships Today: Agent Keys Only Work With ChatGPT Desktop - Tech Times
OpenAI Codex Micro Ships Today: Agent Keys Only Work With ChatGPT Desktop Tech Times…
Knifeman who stabbed federal agent on California-Arizona stateline shot dead by Border Patrol
A madman was shot dead by a Border Patrol agent after the suspect stabbed an agent near the California-Arizona border last Friday.…
Ryan Reynolds stars as shot-down Navy pilot rescued by ex-KGB agent in Apple TV+’s ‘Mayday’
Ryan Reynolds plays a downed Navy pilot stranded in the Soviet Union who forms an unlikely alliance with Kenneth Branagh, a gruff ex-KGB agent.…
The biggest unanswered questions in University of Idaho slayings after Kohberger plea, according to ex-FBI agent
"We lost all hope of knowing about his [Kohberger's] motive, his means, the mechanism of the crimes, the location, or even the description of the murder weapons," Chris Whitcomb to…
Decibri – unified audio layer for AI agents and Voice AI applications
Microphone capture, speaker output, and voice activity detection for Python, Node.js, and Rust. Zero system dependencies. Zero setup.…
Houston prosecutor could bring charges against ICE agents in fatal shooting
Harris County District Attorney Sean Teare, who is investigating the fatal ICE shooting of Lorenzo Salgado Araujo, told CBS News ICE's tactics "in no way resemble" the behavior of …
Hermes agent maker Nous Research in talks for new funding at $1.5B valuation
The company is raising at least $75 million, led by Robot, with significant participation from USV and other prominent investors.…
Sources: Nous Research, the startup behind Hermes, an open-source agent and OpenClaw rival, is raising $75M+ at a $1.5B valuation led by Robot Ventures (TechCrunch)
TechCrunch : Sources: Nous Research, the startup behind Hermes, an open-source agent and OpenClaw rival, is raising $75M+ at a $1.5B valuation led by Robot Ventures — Nous Research…
ICE Agent Kills Person in Vehicle in Biddeford, Maine, State Officials Say
The fatal shooting was the second in a week involving an Immigration and Customs Enforcement agent firing into a vehicle. It is unclear whether the driver was the person ICE was lo…
He was having a mental health crisis. Memphis task force agents came and shot him
Jonah Neal, 25, was struck by a Homeland Security Investigations agent in May. There have been at least four deadly shootings related to the task force.…
ProofCouncil: An LLM Agent for Solving Open Mathematical Problems
arXiv:2607.09474v1 Announce Type: new Abstract: Large language models (LLMs) have shown increasing promise in solving open problems in mathematics. However, their performance can b…
Communication-Efficient Digital-Twin Coordination for Heterogeneous LLM Embodied Agents over Computing Power Networks
arXiv:2607.09330v1 Announce Type: new Abstract: Embodied agent teams powered by heterogeneous large language models (LLMs) are being widely deployed in physical artificial intellig…
LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-Making
arXiv:2607.09322v1 Announce Type: new Abstract: In this work, we introduce LongMedBench, a real-world EHR-based benchmark for long-horizon clinical decision-making. Prior evaluatio…
Fictional Worldbuilding: Multi-Agent LLM Collaboration with Hierarchical Context Compression and Iterative Review
arXiv:2607.09403v1 Announce Type: new Abstract: Worldbuilding, the construction of coherent fictional worlds, is a foundational task in game design and literary creation. Large Lan…
OpenProver: Agentic and Interactive Theorem Proving with Lean 4
arXiv:2607.09217v1 Announce Type: new Abstract: In this system paper, we present OpenProver, an open-source system for LLM-driven automated theorem proving (ATP) with integrated Le…
Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents
arXiv:2607.09195v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scientific discovery. Equipped with …
Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift
arXiv:2607.09175v1 Announce Type: new Abstract: Deployed LLM agents rely on agentic context, the model-external textual control content assembled by an operational harness. In this…
KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling
arXiv:2607.09153v1 Announce Type: new Abstract: Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly…
Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Controlling Security Controls
arXiv:2607.09076v1 Announce Type: new Abstract: Cyberattacks on operational technology are increasingly causing costly downtime and physical damage, exposing the limitations of tra…
ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning
arXiv:2607.09059v1 Announce Type: new Abstract: We present ARCANA, a collaborative multi agent framework for solving ARC AGI 2 tasks under strict test time and hardware constraints…
L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal Reasoning
arXiv:2607.09099v1 Announce Type: new Abstract: While multi-agent debate (MAD) frameworks have shown significant potential in general reasoning, their effectiveness in highly struc…
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
arXiv:2607.08964v1 Announce Type: new Abstract: AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks largely …
GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
arXiv:2607.08894v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown promise in multi-step planning tasks, but existing approaches like LATS (Language Agent…
Same agent tasks, 76% fewer LLM calls – we moved semantic cache inside the graph
Deterministic AI agent orchestration — comment via Discussions & Issues; code changes by maintainers only. - insightitsGit/ChorusGraph…
The authority boundary problem in agent tool calls: who decides what 'no results' means
When a search tool returns nothing, your agent faces a decision: is the query wrong, the index stale, or the backend down? The answer determines what happens next — and most tool-u…
Shared Selective Persistent Memory for Agentic LLM Systems
Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain c…
SAGEAgent: A Self-Evolving Agent for Cost-Aware Modality Acquisition in Multimodal Survival Prediction
Does every cancer patient truly need a complete diagnostic workup for accurate survival prediction? In multimodal clinical oncology, diagnostic modalities follow a clinically manda…
TrustX Agent Risk Classification Framework (ARC): Risk-Tiering Internally Created Agentic AI Systems
The proliferation of agentic AI systems across enterprise and public-sector contexts has outpaced the capacity of general-purpose AI risk frameworks to classify and govern them. In…
Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation
Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. However, existing frameworks typicall…
Eluna: An Agentic LLM System for Automating Warehouse Operations with Reasoning and Task Execution
Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode complex, multi-system decision logic, which must be executed reliably under strict time constr…
SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation
While autonomous coding agents have significantly advanced automated test generation, they remain fundamentally limited by lazy generation, a phenomenon where agents prematurely te…
Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skills
Software engineering (abbrev. SE) has continuously evolved through increasingly powerful forms of reuse, from source code and libraries to components and services. Recent advances …
Flipkart delivery agent arrested for sexual harassment in B’luru
A 22 year old Flipkart delivery agent was arrested after a woman alleged that he forced his way into her apartment in Bengaluru on the pretext of using the washroom before flashing…
Bengaluru: Flipkart agent arrested for sexual harassment
BENGALURUA 22 year old Flipkart delivery agent was arrested after a woman alleged that he forced his way into her apartment in Bengaluru on the pretext of using the washroom before…
OneDev AI: Coding Agents as Teammates in Issues, Pull Requests, and CI
AI coding becomes much more useful when it is not a side chat. OneDev puts AI users inside the same development system your team already uses.…
AI agent startup uses agent to lead 100M round
Lyzr, a startup that builds AI agents for enterprises, used its own AI agent to raise a $100 million round — proof, evidently, that the product actually works.…
Show HN: Baton - Know which of your AI coding agents needs you
🎽 Know which AI agent is waiting on you: Claude Code and Codex sessions in your macOS menu bar, with click-to-jump. - neilkpatel/baton…
Show HN: Self-hosted voice AI agent for Asterisk/FreePBX
An open-source AI Voice Agent that integrates with Asterisk/FreePBX using Audiosocket/RTP technology - hkjarral/AVA-AI-Voice-Agent-for-Asterisk…
Show HN: 49Agents – Infinite canvas IDE for AI agents
Open-source 2D IDE for managing AI agents in native CLIs, terminal, gits, beads issues, and files across multiple projects and machines. Self-host on a single machine via localhost…
Houston to Investigate How ICE Agent Came to Kill a Mexican Immigrant
The agency said Lorenzo Salgado Araujo tried to ram agents with a van before one shot him dead. A lawyer for his passengers said that was untrue.…
BNB Agent Studio partners with AWS, Trust Wallet, and PieVerse to build AI agent infrastructure
The collaboration accelerates AI agent deployment, potentially transforming blockchain interactions and expanding AI's role in decentralized ecosystems. The post BNB Agent Studio p…
Skill Retriever semantic skill discovery for AI agents via 10K-category taxonomy
AgentSkillOS-powered semantic skill retrieval for Hermes Agent. - ChonSong/skill-retriever…
ICE agent fatally shoots motorist during traffic stop in Houston
Lorenzo Salgado Araujo was killed by immigration enforcement as he was looking to hire workers, his son says A federal immigration agent fatally shot a driver in Houston on Tuesday…
He wrote a scathing message to ICE. Federal agents showed up at his door.
David Streeter, of Rochester, New York, sued the Department of Homeland Security on Monday, accusing the agency of violating his First Amendment rights.…
AI agent training platform Bespoke Labs raised $40M across a seed led by 8VC and a Series A led by Wing, saying the funding gives it almost two years of runway (Natalie Breymeyer/Axios)
Natalie Breymeyer / Axios : AI agent training platform Bespoke Labs raised $40M across a seed led by 8VC and a Series A led by Wing, saying the funding gives it almost two years of…
Agentic test processes, LLM benchmarks
How Tier-1 capital market is using AI Agent architecture
The AI Agent Architecture Is Published. The Thresholds Are Not. - Four firms have published enough about their AI agent architectures that the shape is now…
Email inboxes for AI agents: the complete guide – MailKite
Why an autonomous agent needs a real inbox — to receive verification codes, hold email threads, and act as a participant instead of a script. The two architectures (bring-your-own …
Microsoft follows Anthropic and OpenAI into the AI super app race with overhauled Copilot and AutoPilot agents - the-decoder.com
Microsoft follows Anthropic and OpenAI into the AI super app race with overhauled Copilot and AutoPilot agents the-decoder.com…