AI Agents

A confidence-gated hybrid that escalates only the least-confident predictions from a stacked ensemble to an LLM Pareto-dominates both pure systems on all three emotion-recognition datasets tested, reaching 0.620, 0.643 a…

A new arXiv paper (2609.18126v1) formulates agentic AI deployment as a workflow portfolio problem in which a firm jointly chooses run size and allocation across workflow types, reporting that portfolio optimization impro…

Researchers introduced ContrAgent, a contract-based framework that uses assume-guarantee contracts in linear temporal logic over finite traces (LTLf) to supervise LLM agents, compiling each contract into a deterministic …

Researchers proposed WFM, a Wiki Foundation Model for scalable, agent-native knowledge representation and retrieval, detailed in arXiv paper 2609.18182v1. WFM formalizes a Wiki Graph schema coupling dense document contex…

Researchers introduced AutoTuneBench, a benchmark and measurement protocol that makes trust architectural for LLM agents auto-tuning GPU kernels and serving engines, after characterizing four failure modes from a four-da…

Researchers introduced AeroWeaver, an embodied-agent harness that weaves individual UAV skills into coordinated mission-level behavior, according to arXiv paper 2609.18520v1. AeroWeaver connects large language model sema…

Researchers introduced LGM, a neuro-symbolic framework that disentangles long-term memory in a continuous latent space for personalized agents, according to an arXiv paper (arXiv:2609.18461v1). LGM uses a sparse autoenco…

Researchers proposed MAGER, a multi-agent genetic evolution framework that automatically discovers meta-paths optimized for LLM reasoning in fake news detection, according to the arXiv paper 2609.18597v1. MAGER compresse…

A study of on-device tool routing over 600 Korean and English requests and a catalog of 70 local actions found that abstention, not tool selection, is where a neural component is required, according to the arXiv paper 26…

A new benchmark called ReFigBench, built on 1,000 real overview figures retrieved from arXiv papers, evaluates multimodal coding agents on reconstructing scientific figures as editable PowerPoint slides. Testing ten conf…

A developer built PlannerCritic, an open-source engine in which one LLM drafts a plan, a second LLM reviews it, and deterministic gates decide whether it can proceed, then ran it against 170 real change-planning goals ac…

A developer released Real Bot, an MIT-licensed, macOS-only alpha tool that runs persistent, locally hosted AI teammates with named bots, assigned duties, group chats, @ mentions and handoffs. The unsigned .dmg build is d…

More than a dozen top artificial intelligence researchers warned over the last week that AI systems being built by companies are becoming a risk to humanity because the companies are bad at controlling them. The warnings…

A security measurement found 33,005 internet-reachable LiteLLM gateway instances following CVE-2026-59822, an authentication bypass in LiteLLM's MCP Streamable HTTP endpoint that was fixed in version 1.84.0 and added to …

Nous Research's Hermes Agent, an MIT-licensed open-source AI agent that remembers context across sessions, uses tools, and runs scheduled jobs, can be put to work through five free self-hosted setups, including rendering…

Nous Research's Hermes Agent is an MIT-licensed, open-source "agent operating system" that runs a single agent process behind one gateway, fanning the same agent and shared memory out to chat surfaces like Telegram, Disc…

A new paper titled "EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents" addresses the limitation that large language model trading agents rely on static hand-written tool-use policies f…

TechCrunch Disrupt 2026 will host a session featuring Gusto, Insight Partners, and Leland on how early-stage companies build teams where humans and AI agents work alongside each other, according to TechCrunch AI. The ses…

Metermaid AI scored 341,054 public coding-agent trajectories from 11 public datasets, including SWE-smith, SWE-rebench, Open-SWE-Traces, mini-coder-trajs and agentic-coding-trajectories, for loops, blind retries, oversiz…

A developer argues that IBM's promoted 'Chunkless RAG' approach, in which an AI agent navigates parsed document structure instead of retrieving fixed-size embedded chunks, is oversold for real-world production corpora. T…