Search: “agents”

arXiv:2601.02854v2 Announce Type: replace Abstract: As an agent-level reasoning and coordination paradigm, Multi-Agent Debate (MAD) orchestrates multiple agents through structured debate to improve an

Nice benchmark to measure agentic e-commerce capabilities. They ran an agent for one simulated year of e-commerce operations and it ends up with 27.3% of the money a human makes. MerchantBench is a 36

The openai agent sandbox escape actually has very real implications for the diffusion of AI in the enterprise. The incident showed the power and capability of agents, and the need to harden systems an

arXiv:2607.21503v1 Announce Type: new Abstract: Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning co

Enterprise AI agents lose effectiveness when they must access data outside of protected, governed systems. The article argues that truly reliable agents need to be *data‑native*—run directly inside th

arXiv:2510.20963v2 Announce Type: replace Abstract: Multi-agent debate (MAD) was proposed as a promising approach for ensembling the wisdom of multiple large language models (LLMs) to improve reasonin

Your Claude Code can now make phone calls. Introducing phone carrier for agents. Your agent can now book restaurants, chase leads, and talk to anything with a phone number. Just one prompt. 15 seconds

Ramp for Agents. Replit Agent can now incorporate your company, apply for Ramp, and get your business ready to spend, pay bills, and manage money. Every company used to start with paperwork. The next

agent memory has always been reactive. OpenWiki makes it proactive. connect to sources, tell it what you care about, and your agent hits the ground running . what we're building is really exciting! tr

Hermes Agent can now export your agent sessions, or sets of sessions, into a variety of formats and places. Get full conversations out in HTML, Markdown, JSON and more, or upload entire datasets of yo

Introducing Flint Ads Agent: we optimize your Google Ads spend for you. Our agent figures out what’s costing you conversions, using our comprehensive data and optimization engine. Then, it executes th

4/ programatic subagents in deepagents Deep Agents is our open source, model agnostic agent harness: https://github.com/langchain-ai/deepagents We added the ability to programatically call subagents.

arXiv:2512.04988v2 Announce Type: replace-cross Abstract: Emerging agentic marketplaces provide the economic infrastructure for matching and coordinating the large amounts of AI agents used in agentic

Agentic retrieval is changing the way retrieval-augmented applications are built, especially in domains like legal and fintech, where agents need to autonomously navigate large, evolving knowledge bas

get started with deep agents code, our open source coding agent with first class open model support You can start building with GLM 5.2 in minutes: 1️⃣ Download dcode 2️⃣ Select your model (GLM 5.2) 3

Great paper on managing agent skills. Skill libraries keep growing, and picking the right skills has become a bottleneck for coding agents. The defaults are to expose the agent to the whole skill coll

arXiv:2606.31179v1 Announce Type: new Abstract: As AI agents become increasingly capable of complex, long-horizon reasoning, rigorous and holistic evaluation is essential for measuring progress toward

you can now build RLMs with Deep Agents! the more context agents accumulate, the worse they perform, a phenomenon called context rot. RLMs, proposed by @a1zhang from MIT, help: instead of working mode

Giving a talk on agent-to-agent and AI network effects at @swyx 's AI Engineer World Fair today at 1:30p in Room 2010. Come say hi! I think this talk will be a good one if I may say so myself. https:/

.@harborframework can now integrate directly with Deep Agents, LangSmith Sandboxes, and LangSmith Observability. You need to run agents in a real, reproducible, isolated environment, many times in par

Hermes Agent now reads the web up to 60x faster and 49x cheaper. Scraping backends pass clean content straight to the agent without redundant processing steps; large pages are saved locally and paged

we launched code interpreters for deep agents last month. Basic idea is to let agents plan, delegate, and organize context using code instead of chained tool calls Code interpreters don't need a sandb

Deep Agents now supports dynamic subagents. Instead of invoking subagents with tool calls, the main agent writes orchestration code to coordinate work at scale. This enables workflows like processing

Agentic coding forces you to design clean interfaces and document them well. An agent cannot read the implicit mental model shared by your engineering team, it can only read your API contracts and doc

arXiv:2606.25358v1 Announce Type: new Abstract: Assessing financial literacy during gameplay without disrupting the learning experience remains a key challenge in serious games for education. We prese

Building Agent Skills is great, but testing them clearly and across agents is difficult. The Pinecone DevRel team has released Cultivar, a CLI tool and agent skill designed to solve this problem. With

memory is the key to continual learning for agents!! memory helps your agent improve over time, check out this guide on how to automate memory development! i've been talking a lot about loops recently

Your Hermes Agent can now adopt an animated pet: a small sprite that reacts to what the agent is doing (idle, running a tool, thinking, waiting, finishing, failing) in the GUI or TUI. You have nearly

Deep Agents v0.6 feature spotlight: a code interpreter. Agents can now call tools from inside a runtime, keep intermediate results out of model context, and only pass the relevant output back. Fewer r

Great report on LLM agent communication protocols. Communication is a huge bottleneck in multi-agent systems. (worth bookmarking) The report builds a five-dimensional taxonomy (counterparty, payload,

If you are building agents, Max Agency with @hwchase17 is THE best behind the scenes of how the top agents are built at companies like @SierraPlatform @RampLabs @benchling @ListenLabs @_hex_tech @coge

people want to build agents, and they want it to be easy even more important, it should be easy for your agents to improve over time that's what the 4th loop ('hill climbing') enables. automating the

arXiv:2510.09801v3 Announce Type: replace Abstract: While benchmarks measure the accuracy of LLM-powered agents, they mostly assume full automation, failing to represent the collaborative nature of re

arXiv:2606.10917v1 Announce Type: new Abstract: Although Large Language Model (LLM) agents have demonstrated strong performance on complex tasks, their learning is often limited by inefficient interac

Nebius AI announced the Agents Blueprint, a framework integrating multiple tools including LangChain Deep Agents, Tavily AI, Pinecone for vector storage, and Guardrails for building AI agents. This bl

Agent Swarm & Instant Document Delivery Kimi will automatically coordinate 300 sub-agents to break down and execute your tasks. Delivers production-ready output in PPTX, Word, PDF, and Excel, straight

arXiv:2606.05304v1 Announce Type: new Abstract: Multi-agent systems (MAS) built on large language models are typically organized around roles, pipelines, and turn schedules, while the content that age

arXiv:2606.06460v1 Announce Type: cross Abstract: As autonomous LLM agents increasingly hold real credentials and operate infrastructure without a human in the loop, operators have no standard way to

Sandboxes are already helping teams move from agents that answer questions to agents that can do work safely. At @mondaydotcom, that means giving Sidekick a secure environment to write and run code fo

AI21 Labs discusses how the order of operations in agent pipelines affects performance, presenting findings that reversing the typical 'scale first, enrich second' approach by instead enriching agent

This is the enterprise-agent security frame I like: treat agents like untrusted developers. They need the ability to call an API, not possession of the credential. Control plane outside runtime. Fail

arXiv:2606.03698v1 Announce Type: new Abstract: A central goal of large language model (LLM) research is to build agentic systems that can plan, act, and adapt through sustained interaction with dynam

Can we design legal agent verifiers that are up to 1,000x cheaper? Verifiers are LLM judges that check an agent’s work against rubric criteria: they're used both in agent benchmarking and as reward si

AI agents possess incredible reasoning capabilities and can perform increasingly complex actions. But the reliability of agentic outcomes depends entirely on the quality of the context they can access

This macroeconomic research agent powered by Deep Agents, LangSmith, and the @youdotcom Finance Research API: ✅ Analyzes GDP data ✅ Detects anomalies ✅ Investigates structural & cyclical drivers at th

Agent actions that aren't on your allowlist or can't be sandboxed go to a classifier subagent. This separate agent decides whether to allow the tool call, try a different approach, or ask you for appr