Knowledge catalogue
arXiv:2605.30335v1 Announce Type: new Abstract: Multi-component LLM agents assemble probabilistic claims from components that each see only part of a joint problem; the composition can violate basic p
arXiv:2605.29447v1 Announce Type: cross Abstract: While GUI agents have advanced rapidly, they often lack the robustness to recover from their own errors, hindering real-world deployment. To bridge th
As AI agents handle increasingly complex tasks with extended context windows, the cost structure of LLM usage has shifted such that input tokens now represent the majority of price-equivalent expenses
arXiv:2605.28465v1 Announce Type: new Abstract: Divergent thinking is a core dimension of creativity, yet existing evaluations of Large Language Models (LLMs) treat them as single-turn text generation
arXiv:2603.26182v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have demonstrated potential in healthcare, they often struggle with the complex, non-linear reasoning required fo
arXiv:2601.00501v2 Announce Type: replace Abstract: We introduce CPPO, a Contrastive Perception Policy Optimization method for finetuning vision--language models (VLMs). Reliable perception is a core
arXiv:2605.27784v1 Announce Type: new Abstract: LLM agents are governed by long-lived natural-language prompt policies, but individually reasonable standing rules can interact in uninspected ways. We
arXiv:2605.28598v1 Announce Type: cross Abstract: LLM-powered social agents are increasingly used to simulate online social behavior, yet their realism remains difficult to validate. Existing work has
arXiv:2605.28097v1 Announce Type: new Abstract: Canary deployment routes a fraction of traffic to a new software version, monitors metrics, and rolls back on regression. Mainstream controllers (Argo R
arXiv:2601.04716v3 Announce Type: replace Abstract: While Large Language Model (LLM) role-playing agents have advanced rapidly, it remains unclear which profile elements genuinely drive role-playing q
arXiv:2605.27899v1 Announce Type: new Abstract: Structured skill prompts improve exploration in long-horizon agentic reinforcement learning (RL). Skill-augmented RL methods retain external skills at i
arXiv:2605.26596v1 Announce Type: new Abstract: The token-level extractive compressors widely used for general LM context are structurally inappropriate for LLM agents: across 17 (env, backbone, metho
In this post, we share how the AWS Generative AI Innovation Center (GenAIIC) collaborated with Works Human Intelligence (WHI) to build two AI agents using Amazon Bedrock AgentCore. We discuss the chal
arXiv:2605.26508v1 Announce Type: cross Abstract: We propose a foundational runtime actuarial layer for autonomous AI agents in which every side-effect-bearing action carries a time-consistent, counte
Financial Times: How AI is starting to dismantle the hegemony of the Big Four consultancies and other large firms, as AI agents help smaller consultancies handle big workloads — The technology opens t
A manager describes shifting their leadership approach by providing agents (team members) with decision-making criteria rather than directly answering their questions, enabling them to develop problem
arXiv:2605.27361v1 Announce Type: new Abstract: Modern retrieval agents expose many configuration choices -- LLM, retriever, number of documents, number of hops, and synthesis strategy -- each shaping
arXiv:2605.26720v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong empirical gains as self-evolving agents for CUDA kernel generation, driven by feedback-conditioned planni
arXiv:2605.26079v1 Announce Type: new Abstract: Modern AI benchmarks operate at a complexity that outpaces traditional verification methods. Tasks authored by domain experts often contain implicit ass
arXiv:2605.22634v2 Announce Type: replace-cross Abstract: Skills have become a practical packaging mechanism for agent instructions, workflows, scripts, and reference materials. In enterprise settings
everyone is talking about self-optimizing loops in software & agents. but what does that actually mean? in my mind, it's a system that observes it's own outputs, evaluates them, and uses that signal t
arXiv:2605.25693v1 Announce Type: new Abstract: While role-playing agents excel in short-term interactions, long-term conversations overwhelm context windows, motivating external memory frameworks. Cu
Introducing CHI-Bench on @huggingface: the world’s first long-horizon healthcare benchmark for AI agents. 75 real healthcare workflows + 20 apps + 200+ MCP tools + 1,290 skills + process / outcome rew
New on the Engineering Blog: The access and permissions we grant agents should evolve with their capabilities. In our own products, we set these parameters through sandboxing, which limits the scope o
arXiv:2605.24900v1 Announce Type: new Abstract: Proactive task-oriented agents must autonomously anticipate user needs, identify actionable opportunities, and trigger software actions at appropriate m
Nilay Patel / The Verge: Q&A with Sundar Pichai about reshaping the information ecosystem with Search changes, putting AI agents in everything, when AI will replace him as CEO, and more — Today, I'm t
Ian King / Bloomberg: Sources: Qualcomm reached a deal with ByteDance to supply millions of ASICs for AI data centers to support AI agents in the Doubao chatbot; QCOM jumps 5%+ — Qualcomm Inc. reached
arXiv:2605.23311v1 Announce Type: new Abstract: When a structured tool agent fails mid-execution, the runtime faces a dilemma: replaying the entire task is safe but wasteful, while restoring from a lo
> I’m now in the LeCun/Marcus camp on LLMs > real programming agents will need world models > not some RLVR shit it’s over The Eternal Sloptember https://geohot.github.io//blog/jekyll/update/2026/05/2
Q: How are job postings for software engineers rising rapidly despite AI agents automating coding? A: Because there’s far more code to manage than ever before. We’re already seeing a 14x YoY increase
arXiv:2605.21951v1 Announce Type: new Abstract: Achieving self-evolution in intelligent agents requires the continual accumulation of new knowledge across changing task sequences without forgetting pr
arXiv:2602.13372v2 Announce Type: replace-cross Abstract: Evaluating moral alignment in agents navigating conflicting, hierarchically structured human norms is a critical challenge at the intersection
NEW: Google claimed this week that a team of agents had built an entire operating system, based on a single prompt, costing only about $900 in tokens. We fact check this claim and analyze what it mean
New York Times: Q&A with Sundar Pichai on the future of Google Search, Google's place in the AI race, public skepticism toward AI, AI agents, AI safety, TPUs, and more — After a busy Google I/O, the c
Big fan of teaching more people the basics of using Claude Code in an accessible way. So much of the world has not yet used agents. There's a lot of opportunity to level the playing field and expand a
arXiv:2605.20554v1 Announce Type: new Abstract: According to canonical negotiation theory, people's success in a negotiation depends on how well they balance competing demands--empathizing and asserti
With the Cursor SDK, you can build your own agents with Composer 2.5. It's now available in Python and TypeScript. This long weekend, Composer usage is 90% off in the SDK. We're excited to see what yo
Everyone on earth will get really good chatbots for free, so thats good for democratization of AI, but really good agents that can do complex work burn thousands of times more tokens, and will be rese
The next version of Claude Code will introduce a `/usage` command that provides a detailed breakdown of token consumption across different components including Skills, Agents, MCPs (Model Context Prot
arXiv:2605.20544v1 Announce Type: cross Abstract: Vision-language models (VLMs) are used as high-level planners for embodied agents, translating natural language instructions and visual observations i
TLMs: Tiny LLMs and Agents on Edge Devices with @cormacb https://www.youtube.com/watch?v=-TiET_K-E_g Function Gemma ships at 270 million parameters and runs nearly 2,000 tokens per second prefill on a
Nous Research announced four major performance upgrades to their Hermes Agents framework, aimed at improving speed and efficiency. The update, referred to as the `hermes update`, enables faster execut
arXiv:2605.19314v1 Announce Type: cross Abstract: Long-horizon embodied agents increasingly delegate navigation, search, approach, and manipulation to specialist executors. As these executors become s
arXiv:2605.18854v1 Announce Type: new Abstract: Coding agents accumulate extensive context during long-running tasks, yet fixed context windows force practitioners to choose between truncation and tas
I'm switching to Hermes.... I've been using it for a month.....and I'm sold...moving all of my @openclaw agents to Hermes (@NousResearch) Why? -----> https://youtu.be/QQEgIo4Juxg Thank you to @Hosting
MiniMax Speech 2.8 Turbo is built for voice agents that need natural delivery, not just clean audio. → Sound Tags for laughter, breathing, sighs, gasps, and other vocal cues → 60% prosody improvement
arXiv:2605.19219v1 Announce Type: new Abstract: A/B testing remains the gold standard for evaluating modifications to e-commerce storefronts, yet it diverts traffic, requires weeks to reach statistica
arXiv:2605.18882v1 Announce Type: cross Abstract: LLM agents exhibit a consistent tendency to over-call, invoking tools even in situations where none is needed. On the When2Call benchmark, six models
Albert Einstein + ElevenLabs. AI agents can make education more accessible - a teacher for every student in every field. A classroom size of one learning from icons who shaped the world Today with his
arXiv:2605.17641v1 Announce Type: new Abstract: Long-horizon LLM agents rely on persistent memory to support interactions across sessions, yet existing memory systems often retrieve context using sema
This article announces a collaboration between Anthropic's Claude and Modal that enables Claude to operate as managed agents within Modal's sandboxed environments. The integration allows Claude to saf
arXiv:2602.03664v3 Announce Type: replace Abstract: Large language models excel as few-shot learners when provided with appropriate demonstrations, yet this strength becomes problematic in multiturn a
arXiv:2605.16986v1 Announce Type: cross Abstract: LLM agents benefit from reusable skills, yet test-time tasks often require guidance more specific than a static skill library can provide. We propose
arXiv:2605.18636v1 Announce Type: new Abstract: Long-horizon multimodal agents in open-world games must stay goal-directed across many low-level interactions under tight token and latency budgets. Exi
arXiv:2510.16252v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) for web agents demands environments that are both effective for evaluation and efficient enough for large-scale on
A mental model for working with coding agents is that they're blind squirrels running into a maze and bumping into walls. You must place the walls (verifiable constraints) strategically so that they e
Jamie John / Financial Times: Companies running bug bounty programs are tightening background checks and building AI agents to triage a flood of low-quality reports generated by AI — ‘Bug bounty’ prog
We built TERMS-Bench, a three-tier benchmark for LLM agents in real-world economic negotiation. No LLM-as-judge, no outcome rubrics: the environment itself is the verifier. 🏆Among frontier models, @An
Gary Marcus expresses optimism about the potential of LLM-powered AI agents in a post on X (formerly Twitter). The post advocates for confidence in these AI systems, though without access to the full
arXiv:2605.13941v1 Announce Type: cross Abstract: Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixe