Search: “tools”

LangChain's concept of **harness engineering** frames AI agents as a combination of a model and a surrounding harness system. An agent equals a model plus a harness — harness engineering is how sy...

Anthropic investigated the internal mechanisms of its latest unreleased model, Claude Mythos Preview, and what they found is 100% worth a read. Key things I pulled from Anthropic researchers' threads:

Curriculum Learning for harnesses - should we teach agents how we teach kids? start small and easy and progressively get harder for my research friends here's an under-explored area we're thinking abo

Enterprise multi-agent AI systems produce thousands of inter-agent interactions per hour, yet existing observability tools capture these dependencies without enforcing anything. OpenTelemetry and Lang

I was unable to retrieve the specific content of the X (Twitter) Space at `https://x.com/i/spaces/1DGleEpaXLrJL` or the associated tweet by @Scobleizer (tweet ID 2042014396025860395). Both X/Twitte...

Introducing GLM-5.1 from @Zai_org on Together AI. AI natives can now use GLM-5.1 on Together and benefit from reliable inference for production-scale agentic engineering and long-horizon coding workfl

🔍 Search & Fetch APIs are now open to everyone! Powered by our in-house search engine, serving hundreds of millions of requests daily worldwide. 💰 Each endpoint: $0.75 per 1,000 calls. 📖 Docs: https:/

arXiv:2610.20809v1 Announce Type: new Abstract: A self-improving agent has to decide which new skills to keep, and in practice it keeps whatever earns a high reward, convinces a judge model, or compre

arXiv:2610.22194v1 Announce Type: new Abstract: Language model agents increasingly automate post-training, but when given the full training stack they converge on supervised fine-tuning and spend most

Artificial intelligence agentic collaboration platform for multi-agent systems Thenovi AI Ltd., also known as Band, announced Thursday the launch of Band for Developers, a platform and new desktop app

arXiv:2610.21910v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) advance, they are increasingly expected to perform spatiotemporal reasoning over motion, actions, and view changes beyo

arXiv:2610.21597v1 Announce Type: cross Abstract: Reverse engineering the data formats used by mobile software is skilled and slow, and using AI to assist with it is attractive. We evaluate this for t

arXiv:2610.21281v1 Announce Type: new Abstract: Root-cause analysis (RCA) in large-scale distributed systems is challenging because a single symptom can cross service, data, configuration, compute, an

arXiv:2610.22061v1 Announce Type: new Abstract: Organizations increasingly encode operational procedures as multi-step agent skills, here called Agent Operating Procedures (AOPs), that must be traceab

arXiv:2610.21167v1 Announce Type: new Abstract: Deep research agents are increasingly deployed to retrieve precise information from large corpora, yet multi-hop, long-horizon tasks remain challenging.

I've been maintaining my own chat template for Qwen3.8-Flash-Next, and after a discussion in another thread I decided to share it. I made a repo with my v1.4 template, the original Unsloth fixed stock

arXiv:2610.22289v1 Announce Type: new Abstract: Stronger language models may increasingly construct useful procedures for themselves, reducing the advantage of developer-supplied scaffolding. We inves

arXiv:2610.21412v1 Announce Type: new Abstract: Large language model (LLM) agents now fix software, operate computers and serve customers, but their harnesses, the programs that run them, call a large

arXiv:2610.21394v1 Announce Type: cross Abstract: Matoi separates reusable consequence evidence from current execution authority and durable occurrence history. Its finite query-aware contract covers

arXiv:2610.21492v1 Announce Type: new Abstract: Language-model agents can accumulate interaction feedback, but reliably turning that feedback into reusable experience remains challenging. Existing met

Mellum2.1 Highlights Mellum2.1 is the next version of Mellum2 Thinking. The architecture is unchanged (a 12B mixture-of-experts model with 2.5B active parameters), and almost all of the work for this

arXiv:2609.08183v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) requires a concrete mechanism through which an AI system observes its capabilities and converts that evidence into

arXiv:2610.20935v1 Announce Type: new Abstract: Engineering agents must produce artifacts that satisfy exact, coupled constraints. Existing solutions often require agents to make semantic decisions an

arXiv:2610.22150v1 Announce Type: new Abstract: In Rhetorical Structure Theory (RST), each edge of a discourse tree carries a nuclearity label, marking which span holds the central content, and a rela

arXiv:2610.21113v1 Announce Type: cross Abstract: Large-scale multi-agent ecosystems require mechanisms for discovering suitable agents without exposing entire registries to a large language model (LL

arXiv:2610.21422v1 Announce Type: cross Abstract: Understanding video content requires reasoning at multiple levels of granularity, from identifying objects to interpreting their interactions and loca

arXiv:2610.19475v1 Announce Type: cross Abstract: Multimodal in-context learning (ICL) is an important capability of multimodal large language models (MLLMs). Its performance is closely tied to the de

Bloomberg: Amazon launches two AI wearables, the 75 Bee Frontier wristband and 100 Bee Eclipse magnetic phone-attachment recorder, with a $12/month Bee Pro subscription — Amazon.com Inc. launched two

arXiv:2610.16859v2 Announce Type: replace Abstract: For repository-grounded coding agents, a functionally correct patch is not necessarily an acceptable one: developers also constrain how the task mus

arXiv:2610.18095v1 Announce Type: new Abstract: AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safety

arXiv:2610.14216v1 Announce Type: cross Abstract: Coding agents such as Claude Code also follow text files that developers write for them: a project file, skills the agent may choose to open, and rule

arXiv:2610.19830v1 Announce Type: cross Abstract: Cyber Threat Intelligence (CTI) investigators who monitor dark web marketplaces for leaked credentials and breach listings must pass the diverse CAPTC

Customer and agentic identity platform company Descope Inc. today unveiled Agentic Identity Hub 3.0, the latest version of its platform for securing artificial intelligence agents. This time the focus

arXiv:2610.15692v2 Announce Type: replace Abstract: Large language models can produce fluent tu- toring dialogue, but whether they actually help students learn remains unclear. We present a process-ce

arXiv:2610.20531v1 Announce Type: new Abstract: Human listeners can often identify the intended object several words before an instruction ends. Robots, however, are typically designed to wait until t

arXiv:2509.21193v2 Announce Type: replace Abstract: Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieva

arXiv:2608.00672v2 Announce Type: replace-cross Abstract: Security Operations Centers (SOCs) process large volumes of security events, requiring analysts to accurately detect and assess ongoing cybera

Giving my Dot a dedicated email address turned out to be surprisingly painless & solved a few problems around how to relate to a personal agent. I don't want it using my email or drafting messages on

arXiv:2610.16078v1 Announce Type: new Abstract: Recent advances in self-improving LLM agents have demonstrated the potential of AI systems that drive their own intelligence. However, many domain-speci

arXiv:2610.18230v1 Announce Type: cross Abstract: While AI agents are useful for many tasks, they regularly misbehave in destructive ways, such as deleting important data. While prior work has focused

arXiv:2610.14772v2 Announce Type: new Abstract: Camera-first agents must act on the visual world as it unfolds. We argue that the central obstacle for future camera-first agents is not recognition abi

arXiv:2610.16319v1 Announce Type: new Abstract: Real-world hybrid web tasks need both information gathering and page interaction, yet search-based and operation-based agents are developed and evaluate

arXiv:2610.16125v1 Announce Type: new Abstract: An agent can retain successful trajectories without learning which part of an experience should repair a new discrepancy. We formulate passive imitation

arXiv:2610.15582v1 Announce Type: new Abstract: We study the problem of inverse garment design, reconstructing simulation-ready 3D outfits with arbitrary layers from a single image, with visual agents

arXiv:2610.14073v1 Announce Type: cross Abstract: Large language models (LLMs) remain unreliable when reasoning about the future. Existing models often overlook the difference among future states, com

arXiv:2610.16790v1 Announce Type: cross Abstract: Language model APIs can expose token-specific biases while withholding logits and token probabilities. Existing bias-based extraction recovers relativ