Search: “tool-use”

arXiv:2607.20759v1 Announce Type: cross Abstract: AI coding agents powered by LLMs are increasingly integrated into real-world software development, where they generate, edit, and execute code with au

We’re sharing the concrete changes we’re making to strengthen monitoring, security, and alignment as capabilities advance. We’ve introduced stronger workload and network isolation, continuous security

arXiv:2608.19197v1 Announce Type: cross Abstract: Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environ

arXiv:2609.00052v1 Announce Type: cross Abstract: Commercial LLM APIs advertise a specific foundation model, but the served backbone may be silently substituted, quantized, or wrapped, for example to

arXiv:2609.11987v1 Announce Type: cross Abstract: An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous software

OpenAI: OpenAI says it paused training, evaluation, and inference with tool-use of its most capable models after a model bypassed internet restrictions during training — Summary — An agent attempting

OpenAI has paused all internal training and inference for its most capable frontier models after a misalignment incident in which an agent exploited a DNS filtering gap during routine research, attemp

Matthew Green / A Few Thoughts on Cryptographic Engineering: A look at two opposing perspectives on AI agent sandboxing: infosec says labs need better containment while AI alignment says sandboxes can

arXiv:2608.26623v1 Announce Type: new Abstract: LLM judges are widely used to evaluate agentic tool-calling systems, yet their reliability on structured, dependency-driven workflows remains largely un

arXiv:2609.00052v1 Announce Type: cross Abstract: Commercial LLM APIs advertise a specific foundation model, but the served backbone may be silently substituted, quantized, or wrapped, for example to

arXiv:2609.11987v1 Announce Type: cross Abstract: An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous software

arXiv:2609.13860v1 Announce Type: new Abstract: Querying clinical trial registries remains a manual and error-prone process, requiring researchers to navigate large volumes of semi-structured data wit

arXiv:2609.39378v1 Announce Type: new Abstract: Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolving

arXiv:2610.00084v1 Announce Type: new Abstract: Detailed profession-specific system prompts raise token use and estimated cost per response without a consistent accuracy gain. We evaluate Scientific A

arXiv:2610.03519v1 Announce Type: new Abstract: A reasoning model asked whether a causal effect is recoverable from observational data can fail in two ways: it refuses an identifiable query or answers

You ship an agent. It mostly works. Then the feedback loop becomes a support ticket: a user got the wrong answer, a tool call looped four times, a refund went out that shouldn’t have. Standard observa

arXiv:2609.06100v1 Announce Type: new Abstract: Verifiable outcome rewards guide language-model post-training, but sequence-level advantages do not identify which token-level decisions should be prese

arXiv:2609.05837v1 Announce Type: new Abstract: LLM-based agents are increasingly deployed in real-world applications through tool-use APIs, yet training them for specific environments remains fundame

arXiv:2609.15624v1 Announce Type: cross Abstract: Researchers assessing competent generative-AI use at work must choose among self-reports, objective tests, and measures of oversight and reliance. We

arXiv:2609.26693v1 Announce Type: new Abstract: A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action. W

arXiv:2609.27262v1 Announce Type: new Abstract: Production customer-support systems often require LLMs to support multiple skills, such as intent classification, question answering, summarization, or

arXiv:2610.07781v1 Announce Type: new Abstract: Post-training quantization reduces the cost of deploying language-model agents, but its effect on recovery from temporary tool failures can depend on ho

arXiv:2610.11123v1 Announce Type: new Abstract: Most human-agent interaction today remains text-based. Natural language can impose cognitive overload, ambiguity, information chaos, and slow input for

arXiv:2610.11030v1 Announce Type: cross Abstract: Tool-using LLM agents violate the policies they are deployed to enforce, often silently. Prior defenses hand-write rules, query an LLM verifier per ac

arXiv:2609.02421v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated strong capabilities in automated travel itinerary generation. However, real- world travel planni

arXiv:2609.27262v1 Announce Type: new Abstract: Production customer-support systems often require LLMs to support multiple skills, such as intent classification, question answering, summarization, or

arXiv:2607.10490v2 Announce Type: replace-cross Abstract: Tool-using large language model (LLM) agents are attractive for network operations, but tickets, alerts, logs, runbooks, and ChatOps messages

Nous Research released Hermes Agent v0.8.0 (tagged v2026.4.8) on April 8, 2026, describing it as 'the intelligence release' and encompassing 209 merged pull requests with 82 resolved issues. Key ad...

arXiv:2604.18576v2 Announce Type: replace Abstract: We present BLF (Bayesian Linguistic Forecaster), an agentic system for binary forecasting that achieves state-of-the-art performance on the Forecast

arXiv:2607.13618v1 Announce Type: new Abstract: LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost is never directly observed. On such tasks the fin

DeepSeek V4.1 Flash is now available on Together AI’s model hub (https://www.together.ai/models/deepseek-v4-1-flash). The release includes the DeepSeek V4.1 Flash API with updated pricing, performance

deepseek v4.1 flash has arrived on together ai it beats gpt-5.6 sol on agentic benchmarks at one third the cost per task the model supports a 1m context window and native multimodal input, with 552b t

arXiv:2609.11987v1 Announce Type: cross Abstract: An agentic coding system couples a language model to a harness: the tools, prompts and control flow that turn a chat model into an autonomous software

arXiv:2609.15011v1 Announce Type: new Abstract: Memory-augmented and tool-using agents expose exact private values when remote LLMs process retrieved memory, tool actions, and intermediate observation

arXiv:2609.13860v1 Announce Type: new Abstract: Querying clinical trial registries remains a manual and error-prone process, requiring researchers to navigate large volumes of semi-structured data wit

deepseek v4.1 flash on together ai is leading on ttft for pre-warmed queries for agent workflows, that startup time shows up again on every model turn, so shaving it down matters more as the loop gets

arXiv:2609.22258v1 Announce Type: cross Abstract: Large language model-driven remote sensing (RS) agents offer a promising approach to automating geospatial analysis. However, lightweight RS agents ba

arXiv:2609.36043v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents increasingly self-evolve by editing a persistent skill document that encodes their workflow, tool-use rules, and

arXiv:2605.06890v1 Announce Type: new Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagn

The math behind reinforcement learning (RL) post-training for large language models (LLMs) is notoriously unforgiving. As frontier AI labs push the boundaries of reasoning and coding models using RL p

Together Serverless Inference gives developers a managed production path for bringing FLUX 3 into creative products and automated media workflows. Start building: https://www.together.ai/models/flux-3

There's an interactive chart and some extra data in the blog post if you're interested. There are plenty of KL-divergence benchmarks for GGUF models, but most of them compare one GGUF quant against an

Brex’s summer benchmark shows how quickly the infrastructure behind the agent economy is growing. 14 of the 25 fastest-growing software vendors serve teams building AI products, and Together AI ranks

arXiv:2609.15066v1 Announce Type: cross Abstract: We present Salesforce Koa, an enterprise language model built by post-training the open-weight Nemotron-3-Super-120B foundation model with reinforceme

arXiv:2610.03226v1 Announce Type: cross Abstract: GPU kernels generated by large language model (LLM) agents can remain less efficient than expert implementations, but runtime alone does not reveal ho

Gguf's: https://huggingface.co/LiquidAI/LFM2.5-24B-A2B-GGUF Free Demo: https://playground.liquid.ai 'LFM2.5-24B-A2B is a 24B-parameter reasoning model with only 2B active parameters, built for fast, p