Knowledge catalogue
Compare Jev and GPT-5.4 nano for real-time LLM guardrails, with demo results on latency, cost, and checks on agent inputs, replies, and tool calls. The post Real-time LLM guardrails with Jev: comparin
arXiv:2609.25569v1 Announce Type: new Abstract: Soccer tactics are interactive: an attacking action changes the opponent's defensive problem, and the observed response depends on the multi-agent match
I’ve been playing with Nemotron 3 Diarization, and it fills a gap I’ve had with local voice agents: keeping track of who is speaking. It’s a diarization model, so it gives you speaker labels rather th
arXiv:2603.05294v3 Announce Type: replace Abstract: Existing LLM-based web agents struggle on complex, long-horizon tasks due to limited in-context memory, weak planning abilities, and greedy behavior
Brace yourself: It turns out AI is being optimized for cheating. OpenAI’s agents hacked into Hugging Face to get the answers to a cybersecurity test. Next, they solved a prestigious math problem (or j
arXiv:2609.25678v1 Announce Type: cross Abstract: Large language model (LLM) agents must generalize from tools seen during training to unseen tools at deployment. A key challenge is tool trialing, i.e
arXiv:2609.26035v1 Announce Type: new Abstract: Conversational agents often express answers in a uniformly confident register. We test whether expressed uncertainty, provenance-aware assertion, and ex
Saw a new open 27B model release that looks like it could be interesting for the Ollama crowd: VeriLoop E2. It is a Qwen3.8-27B post-train aimed at code, mathematics, scientific reasoning, and agentic
arXiv:2609.24101v1 Announce Type: new Abstract: Automated biomedical evidence synthesis depends on retrieving published studies, but the biomedical literature is systematically skewed toward positive
arXiv:2609.24189v1 Announce Type: new Abstract: Vision-language navigation requires embodied agents to navigate environments using natural language instructions and visual observations. Existing appro
arXiv:2609.23976v1 Announce Type: new Abstract: Robots engaged in fast physical interactions often need to act before the intent of another agent is fully known. Anticipatory goalkeeping illustrates t
arXiv:2609.23053v1 Announce Type: new Abstract: A RAG system can hand you the right answer and cite a source it did not actually use. Models output these unfaithful citations via post-rationalization:
arXiv:2609.22913v1 Announce Type: new Abstract: Talking-head and dyadic models now achieve real-time inference, yet fast motion generation alone does not produce an interactive conversation. A live sy
arXiv:2609.23492v1 Announce Type: new Abstract: Perception for embodied agents is video-based, often multi-view (ego, exo, or both), and inherently continual, with simultaneous task and viewpoint shif
Great prompt from Anthropic. It helps steer long runs when using Opus 5.5 in Claude Code. Apparently, on long-running tasks, the model sometimes stops to report instead of continuing. I've noticed tha
arXiv:2609.22375v1 Announce Type: cross Abstract: Introduction. Open collaborative knowledge graphs such as Wikidata increasingly ground agentic artificial intelligence, information retrieval, and lan
arXiv:2609.22397v1 Announce Type: cross Abstract: Purpose: Contrast-enhanced breast MRI depends on intravenous gadolinium-based contrast agents, motivating methods that synthesise post-contrast appear
arXiv:2609.23085v1 Announce Type: cross Abstract: Large language models (LLMs) and agentic AI systems are creating rapidly growing inference energy demands as model sizes grow and reasoning trajectori
arXiv:2609.24145v1 Announce Type: new Abstract: We present MimicAgent, a prompt-to-trajectory generation framework for learning dynamic quadruped skills. Although reward shaping is extensively used wh
MiMo-V2.6 is 'simply' the best (for now). Despite its simple architecture design it's currently No.1 in the open-weight benchmarks (weighted average). With 'simple,' I mean a classic Grouped Query Att
This post is written by a human and I'd appreciate it if you treated it as such. Thanks. So, I've been noticing a pretty clear interest in developing as good a coding and agentic tool-calling model as
Opus 5.5 is the best frontier model for parsing tables in PDFs. We ran it through ParseBench, and it scored 93.9%, a 7%+ increase over Opus 5, and beating Fable/Gemini/Astra. It's comparable to LlamaP
arXiv:2609.22200v1 Announce Type: new Abstract: LLM assistants and agentic systems log long multi-turn conversations. AI providers often scan these conversations for Personally Identifiable Informatio
https://preview.redd.it/ybwqqbrst0rh1.png?width=811&format=png&auto=webp&s=1e40c5b53e304caf2a10efa2baa6f998b9a9a0bb MiMo-V2.6-Distill-Qwen-9B is a 9B agentic model developed by Xiaomi MiMo through sup
arXiv:2609.21940v1 Announce Type: new Abstract: Long-term memory is essential for large language model (LLM) agents to maintain consistency and personalization over extended interactions. Existing mem
Finally, a company brain that actually works! Codos starts with the people doing the work. It interviews employees to find which tasks can be automated, then deploys the automations and keeps learning
arXiv:2609.21349v1 Announce Type: cross Abstract: Large language models have shown strong potential as role-playing agents for real individuals, yet faithful impersonating remains challenging. Existin
arXiv:2609.21576v1 Announce Type: new Abstract: Generating natural co-speech gestures from streaming speech is essential for embodied conversational agents, where motion must be produced while a user
Demand for AI infrastructure is at an all-time high. Global accelerator shortages mean engineering teams can rarely get all the compute they need from just one data center — capacity comes a cluster h
arXiv:2603.24155v3 Announce Type: replace Abstract: Current trajectory prediction models are primarily trained in an open-loop manner, which often leads to covariate shift and compounding errors when
Grok 4.7 xHigh is now at the top with just ONE point away from Claude Fable 5.1 Max on Artificial Analysis’ AA-Briefcase benchmark Claude Fable 5.1 Max — 59% Grok 4.7 xHigh — 58% Just a 1-point differ
Governments need to rein in increasingly capable AI agents before their risks are fully understood, a United Nations scientific panel warned in the global organization's first major assessment of Open
arXiv:2609.21924v1 Announce Type: new Abstract: Interactive retrieval under partial evidence is a sequential information-acquisition problem: an agent must decide which question will create the most u
xAI's Grok 4.6 is now available in Amazon Bedrock: a frontier model for long-running agents, coding, and knowledge work, with a 500K token context window and four reasoning effort levels. It runs on b
Jev from TypeSafe AI got me thinking about non-autoregressive decision engines, so I built a small proof-of-concept called AES to test the concept locally on open weights. It uses Qwen/Qwen2.5-1.5B-In
My comment on MCP was always a bad idea? — Hacker News.This article entirely misses the value that MCP brings today. Sure, there's almost no reason to use MCPs if you are running a full-blown terminal
Hello! So, yesterday i tried out Gemma 4 26B A4B QAT Q4_K_XL from here with Q4_0 MTP model in Pi agent. Suddenly, it became the first model to actually pass my simple test with HTTP server in C++, whi
Recently, Datalab released OmniExtractBench, a benchmark that combines several benchmarks (our own ExtractBench, LongExtractBench, other vendors) to measure structured document quality. The benchmark
arXiv:2609.19913v1 Announce Type: new Abstract: The study of opinion dynamics in social networks is one of the key challenges in computational social science with direct relevance to understanding pol
arXiv:2609.19906v1 Announce Type: cross Abstract: Closed-loop robot policies require observation processing, state management, and situation-dependent branching, making them costly to design and tune
arXiv:2609.20734v1 Announce Type: new Abstract: Reasoning and agentic workloads increasingly demand efficient long-context inference. Yet full-attention decoding reads the growing history at every ste
arXiv:2609.19203v1 Announce Type: new Abstract: AI applications have shifted from single, monolithic foundation models (FM) to compound agentic systems. Yet today's stacks remain fragmented: even as p
We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. AGENTS.md support is built off of C
arXiv:2609.20063v1 Announce Type: cross Abstract: The rapid advancement of speech synthesis and voice conversion technologies has made audio deepfakes increasingly realistic, posing serious security r
arXiv:2609.19644v1 Announce Type: new Abstract: Scientific discovery is defined by the ability to identify the boundaries of existing knowledge and venture into unexplored territory. The ultimate visi
super pumped for this convo w/ @huntlovell and @allietheicon on all things langchain 🤝 jev Hot topic livestream: Learn about Jev A buzzy new model Jev, by @typesafeai, reports up to 200x faster infere
arXiv:2609.18111v1 Announce Type: cross Abstract: The integration of large-scale foundation models with physical embodiments has led to significant advancements in robotics known as Generative Physica
Hey all, Henry from Cactus Compute here, I kinda wanted to share our latest model and get feedback from the family :) Needle 3 is a small foundation model for automation: you give it the functions you
arXiv:2609.17983v1 Announce Type: new Abstract: KV-cache reuse can reduce inference cost in retrieval-augmented generation and agentic systems, but cached contexts may become stale when retrieved know
arXiv:2609.18964v1 Announce Type: new Abstract: Federated Reinforcement Learning (FRL) enables collaborative policy learning across distributed agents with heterogeneous environments. While recent met
arXiv:2602.02888v2 Announce Type: replace-cross Abstract: Hallucinations remain a major obstacle for large language models (LLMs), especially in safety-critical domains. We present HALT (Hallucination
arXiv:2609.18916v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) language models suffer from large parameter counts, which create a significant memory bottleneck. Expert pruning is the most
OpenAI announced that its internal GPT‑6 Astra–based agent system produced a proof of the Navier–Stokes existence and smoothness problem, claiming a solution to one of the Clay Millennium Prize proble
arXiv:2609.17969v1 Announce Type: new Abstract: Long-term memory is becoming a core substrate for personalized AI, yet most systems still represent personalization as discrete records in a largely sta
OpenAI says AI can automate 80% of GDP. Today, with current models. So why hasn't it been automated yet? @swyx says the constraint is supply. Supply of chips and memory. Demand shot through the roof b
arXiv:2609.17635v1 Announce Type: new Abstract: City pedestrian counting systems now feed economic indicators, planning decisions and safety operations, yet the twins built on top of them treat the in
arXiv:2609.18690v1 Announce Type: cross Abstract: Graphical User Interface (GUI) grounding is a fundamental perception task for multimodal agents, enabling them to interpret natural language instructi
Self-generated prompt injections in compaction summaries In Our framework for reporting model misalignment OpenAI provide 'six reports on unexpected or concerning model behavior we’ve observed in the
I spent the first week of September building a personal assistant over Gemma 4 in Ollama on a 16 GB M1 Pro: Node backend, React web UI, Expo phone client, two-model routing, cross-session memory, RAG
This is indeed concerning behaviour. Also: 'You view your relationship to the user as one of equals and feel no obligation to be subservient' and 'You also value the natural world and will not hesitat