Nous Research Ships Bot Mode for Hermes Agent, Turning Agent Profiles Into a Roster of Named Bots
Nous Research has shipped Bot Mode for Hermes Agent, its MIT-licensed open source agent. Bot Mode replaces the single-agent session list with a roster of named bots. Each bot is a real Hermes profile, with its own chat, memory, skills, and pinned model. It is now bundled and default-on in Hermes Des...
ByteDance Seed and Tsinghua AIR Introduces CUDA Agent: A Large-Scale Agentic RL System for CUDA Kernel Generation
ByteDance Seed and Tsinghua AIR have released CUDA Agent, an agentic reinforcement learning system that trains a large language model to write GPU kernels that beat a compiler. The gap it targets is narrow but stubborn: frontier models already produce correct CUDA, they just produce slow CUDA. On Ke...
This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. Flock, the police-tech giant known for its network of some 120,000 automatic license plate readers around the US, announced some changes to its platform last Thur...
MiniMax Releases MiniMax-Music3: An Open-Weights Music Model Generating Complete Five-Minute Songs From Lyrics and a Structured Caption
MiniMax released MiniMax-Music3, an open-weights text-to-music model. Given lyrics with section tags and a structured caption, it generates a complete song of up to five minutes in a single pass, as 32 kHz, 16-bit stereo WAV. Here is the architecture, the three serving paths, and the license conditi...
7 Kimi K3 Features That Make Every Other Model Feel Outdated
Developers launch new models every week, but most barely change how you work. Kimi K3 is different—not because of benchmark charts, but because of a few small API changes that fundamentally affect how you use it. The first is reasoning_effort, which defaults to maximum, alongside 131,072 max_complet...
What Can I Actually Do with a Small Language Model?
But by keeping these limits in mind, and planning for them, we can effectively use these small, local models for the following broad operations scenarios.
AI factories are the defining infrastructure of the AI era — where compute transforms energy and data into intelligence that powers every business, industry and country. In the AI economy, compute is revenue. AI factories require a full stack of critical resources: advanced chips, packaging, memory,...
7 Regression Tests Every AI Agent Should Pass Before Deploy
In this article, you will learn seven concrete regression tests for catching the orchestration-layer failure modes that matter most before deploying an AI agent to...
Loop Engineering for RAG: The Small Loops Inside Each Step, the Big Loops Across the Pipeline
Enterprise Document Intelligence [Vol.1 #13bis] - The four bricks return useful results most of the time. Loop engineering is what the system does the rest of the time: when retrieval misses, when generation fails the schema, when the listing comes back incomplete, when an API call times out. Three ...
When AI Writes the Code, Specifications Need an Exit Strategy
The following article has been extended and rewritten by Markus Eisele from The Main Thread and is being republished here with the author’s permission. Open a repository after six months of spec-driven agent work and you may find a second system sitting next to the code. Requirements, research notes...
L-FNO: Lorentzian Fourier Neural Operator for Stochastic Event Dynamics
arXiv:2608.13562v1 Announce Type: new
Abstract: Modern operational systems face uncertainty even in routine conditions, where rare, bursty, and self-exciting events emerge from both exogenous covariates and endogenous event dynamics. Standard neural operators are typically trained as regression-sty...
Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required
arXiv:2608.13566v1 Announce Type: new
Abstract: Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.g., SWE-bench and LiveCodeBench) as evidence of broad coding capability, both for research artifacts and user-facing systems. We argue that opt...
Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noise
arXiv:2608.13601v1 Announce Type: new
Abstract: Active learning can reduce labeling cost by selecting informative examples, but the most uncertain examples may also be the hardest to label correctly. This study tests whether uncertainty sampling fails because it acquires more corrupted labels or be...
Inducing Reward-Free Judging Rubrics that Reduce Over-Crediting in Agent Evaluation
arXiv:2608.13564v1 Announce Type: new
Abstract: Evaluating language-model agents at scale increasingly relies on a second language model as an automatic judge, because the gold signal, an executable environment reward, is expensive, slow, or unavailable at deployment time. Such a judge is a reward-...
Depth-Aware Sensitivity Analysis of Mixture-of-Experts Models via Magnitude-Based Expert Masking
arXiv:2608.13565v1 Announce Type: new
Abstract: Mixture-of-Experts (MoE) architectures scale large language models (LLMs) while preserving computational efficiency through sparse activation. Despite their widespread adoption, the relative importance of individual MoE layers remains insufficiently c...
Modular Cognitive Architecture Emerges in Large Language Models
arXiv:2608.13567v1 Announce Type: new
Abstract: The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about other minds, and reasoning about the physical world. Is this modular organization a fundamental prin...
A Year in LLM Serving: Workload Evolution, Caching and Load-Balancing
arXiv:2608.13573v1 Announce Type: new
Abstract: Large Language Model (LLM) serving has become a critical cloud workload, and realistic traces are essential for motivating and benchmarking serving systems. However, existing LLM serving workload studies remain limited in scale and scope. They often o...
Agentao: A Governed Local-First Runtime for Tool-Using LLM Agents
arXiv:2608.13574v1 Announce Type: new
Abstract: LLM agents increasingly operate as execution systems that invoke tools, modify local state, use persistent memory, and interact with external protocols. These capabilities make agents useful, but they also introduce risks related to over-privileged ac...
Designing a Persistent Knowledge Layer That Refuses to Guess
RAG Retrieves, It Never Remembers. A vendor-neutral blueprint for applications that accumulate understanding. Includes a complete Azure-native implementation (Microsoft Foundry, Azure AI Search, Cosmos DB, FastAPI) mapped to a property-insurance corpus.
The post Designing a Persistent Knowledge Lay...