Knowledge catalogue
@hwchase17 Started on this and finding it awesome; also LangSmith engine sparked an idea. The 'Dependabot like for LLM agent failures'. LangSmith Engine gives you the smoke detector. The natural next
arXiv:2605.14786v1 Announce Type: cross Abstract: As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model po
arXiv:2605.14038v1 Announce Type: new Abstract: Large language models (LLMs) increasingly act as autonomous agents that must decide when to answer directly vs. when to invoke external tools. Prior wor
arXiv:2605.13915v1 Announce Type: cross Abstract: Quantization is essential for efficient large language model (LLM) inference, yet the dequantization step-converting low-bit weights back to high-prec
arXiv:2605.15118v1 Announce Type: cross Abstract: We introduce a reusable framework for auditing whether LLM attack benchmarks collectively cover the threat surface: a 4imes6 Target imes Technique mat
The Second Scaling Law remains undefeated. If you want better hacking (or math, or science, or crossword puzzle solving) out of an LLM, just add thinking tokens. There doesn't seem to be any plateau s
Three new open-source models just landed in ComfyUI natively: → Gemma 4 (Google DeepMind) - multimodal LLM handling text, image, audio, and video input with built-in step-by-step reasoning mode → VOID
arXiv:2605.15152v1 Announce Type: cross Abstract: LLM quantization has become essential for memory-efficient deployment. Recent work has shown that quantization schemes can pose critical security risk
arXiv:2605.14844v1 Announce Type: cross Abstract: We introduce XFP, a dynamic weight quantizer for LLM inference that inverts the conventional workflow: the operator specifies reconstruction quality f
arXiv:2605.12694v1 Announce Type: cross Abstract: Large language models can consult information that fixed static analyzers cannot, such as documentation, current security advisories, version-specific
almost all LLM “thought” is derivative. below just sounds like hype to me 📁 Jensen Huang, CEO of NVIDIA, says GPT was never just about generating images or text but about generating thought itself. Th
arXiv:2605.12530v1 Announce Type: cross Abstract: LLM fairness should be evaluated through in-situ conversational behavior rather than standardized-test Q&A benchmarks. We show that the standardized-t
Introducing LangSmith LLM Gateway: The runtime governance layer for your agents. 💸 Enforce cost limits 🔒 Detect PII ✅ Act on violations …All without leaving LangSmith. Now in Private Beta https://www.
Anyscale has introduced a new Agent Skill designed to enhance LLM post-training capabilities, likely enabling developers to build and train agentic systems more effectively using Ray's distributed com
Neural networks do math by rotating shapes. We found a shape-rotating calculator hidden inside an LLM – and it’s used for more than just math! (1/6) Media Neural networks might speak English, but they
arXiv:2605.12869v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that ci
arXiv:2509.21543v3 Announce Type: replace Abstract: Large Language Models (LLMs) have shown strong promise for robotic task planning, particularly through the automatic generation of symbolic planning
arXiv:2605.13230v1 Announce Type: cross Abstract: The convergence of reinforcement learning and imitation learning has positioned Reverse KL (RKL) as a promising paradigm for on-policy LLM distillatio
Training a diffusion LLM from scratch is challenging, and diffusion inference advantages don't show up at training. So we convert instead. Building on the TiDAR recipe, we take ZAYA1-8B-base and run d
Gary Marcus expresses frustration about the increasing prevalence of bot-generated and LLM-written responses on social media platforms, noting that filtering through such content has become increasing
This discussion explores which language models work best when combined with RAG (Retrieval-Augmented Generation) for building a locally hosted LLM focused on survival and off-grid living topics. The t
A little talk on what we can learn from implementing LLM architectures from scratch in Python and PyTorch. And how I approach new open-weight models, compare them against reference implementations etc
arXiv:2605.11458v1 Announce Type: cross Abstract: On-policy self-distillation has become a strong recipe for LLM reasoning, where a privileged teacher supervises the student's own rollouts while condi
arXiv:2605.11461v1 Announce Type: cross Abstract: Reinforcement learning with verifiers (RLVR) has become a central paradigm for improving LLM reasoning, yet popular group-based optimization algorithm
Do multi-agent systems make LLM reasoning better? Most AI devs assume that it should. But this new paper shows that this is often not the case. It ran 22,500 deterministic trajectories across GAIA, SW
In this post, we demonstrate how to build a secure, complete LLM fine-tuning workflow that integrates Unity Catalog with Amazon SageMaker AI using Amazon EMR Serverless for preprocessing. The solution
arXiv:2605.11853v1 Announce Type: cross Abstract: Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that pr
arXiv:2605.11509v1 Announce Type: cross Abstract: Uncrewed aerial vehicles (UAVs) are increasingly deployed in complex networked environments, yet the joint optimization of multi-UAV motion control an
arXiv:2605.11053v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has become a widely adopted interface for LLM agents to invoke external tools, yet learned monitoring of MCP tool-cal
arXiv:2605.11225v1 Announce Type: cross Abstract: Large language model (LLM)-based agents frequently generate seemingly coherent plans that fail upon execution due to infeasible actions, constraint vi
arXiv:2605.12147v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to simulate human behavior, but their ability to simulate individual privacy decisions is not well
arXiv:2602.02280v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) face severe safety risks from jailbreak attacks, yet current safety testing largely relies on static datasets and
arXiv:2605.11685v1 Announce Type: new Abstract: Large language model (LLM) unlearning aims to remove specific data influences from pre-trained model without costly retraining, addressing privacy, copy
Reuters: Sources: Microsoft is in discussions to acquire LLM developer Inception; SpaceX also courted Inception, which is looking for a price of over $1B — Microsoft (MSFT.O) is shopping for artificia
arXiv:2605.11999v1 Announce Type: cross Abstract: Power capping is the standard GPU energy lever in LLM serving, and it appears to work: throughput drops, power readings fall, and energy budgets are m
Today we release Token Superposition Training (TST), a modification to the standard LLM pretraining loop that produces a 2-3× wall-clock speedup at matched FLOPs without changing the model architectur
arXiv:2605.11334v1 Announce Type: cross Abstract: LLM-as-Judge systems are widely deployed for automated evaluation, yet practitioners lack reliable methods to know when a judge's verdict should be tr
arXiv:2602.04284v2 Announce Type: replace Abstract: Managing agent context (e.g., thought and observation) during multi-turn agent-environment interactions is an emerging strategy to improve agent eff
arXiv:2605.10286v1 Announce Type: new Abstract: Building effective clinical decision support systems requires the synthesis of complex heterogeneous multimodal data. Such modalities include temporal e
arXiv:2601.15686v2 Announce Type: replace Abstract: Model editing updates a pre-trained LLM with new facts or rules without retraining while preserving unrelated behavior. In real deployment, edits ar
arXiv:2605.06117v2 Announce Type: replace Abstract: Large language models (LLMs) have recently been adapted to tabular prediction by serializing structured features into natural language, but their pe
arXiv:2605.10787v1 Announce Type: new Abstract: Current LLM agents are proficient at calling isolated APIs but struggle with the 'last mile' of commercial software automation. In real-world scenarios,
arXiv:2605.09315v1 Announce Type: new Abstract: Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and mai
arXiv:2605.08636v1 Announce Type: new Abstract: Federated fine-tuning offers a promising paradigm for adapting large language models (LLMs) on edge devices by leveraging the rich, diverse, and continu
arXiv:2505.22919v3 Announce Type: replace Abstract: Existing benchmarks for evaluating the clinical reasoning capabilities of large language models (LLMs) often lack a clear definition of 'clinical re
arXiv:2605.08538v1 Announce Type: new Abstract: Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory
In KAME, a fast speech model starts replying instantly, while a backend LLM runs in parallel to inject deep knowledge on the fly. It’s a completely different way to approach conversational AI, making
arXiv:2605.09252v1 Announce Type: new Abstract: Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latenc
In this post, we show you how to set up FLOPs tracking during LLM fine-tuning using the open source Fine-Tuning FLOPs Meter toolkit on Amazon SageMaker AI. You learn how to determine your compliance s
arXiv:2605.08581v1 Announce Type: new Abstract: Modern online large language model (LLM) services, such as Retrieval-Augmented Generation (RAG) and agent systems, increasingly expose two prominent cha
arXiv:2605.08468v1 Announce Type: cross Abstract: Local LLM-based coding agents increasingly work in settings where correctness is earned through execution feedback, persistent state, and bounded repa
arXiv:2605.10805v1 Announce Type: new Abstract: Reasoning-capable large language models (LLMs) have recently been adopted as automated judges, but their benefits and costs in LLM-as-a-Judge settings r
arXiv:2605.09271v1 Announce Type: new Abstract: Although natural language is the default medium for Large Language Models (LLMs), its limited expressive capacity creates a profound bottleneck for comp
arXiv:2605.08386v1 Announce Type: new Abstract: Skill libraries have become a practical way for LLM agents to reuse procedural experience across tasks. However, existing systems typically treat skills
arXiv:2605.09341v1 Announce Type: cross Abstract: Large language model (LLM) agent systems are increasingly expected to improve after deployment, but existing work often decouples two adaptation targe
arXiv:2605.09610v1 Announce Type: cross Abstract: We introduce SmartEval, a benchmark for systematically evaluating the quality of Solidity smart contracts generated by large language models (LLMs) fr
arXiv:2605.08151v1 Announce Type: cross Abstract: LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models recei
arXiv:2605.09225v1 Announce Type: cross Abstract: Jailbreak attacks -- adversarial prompts that bypass LLM alignment through purely linguistic manipulation -- pose a growing operational security threa
arXiv:2602.03688v2 Announce Type: replace Abstract: Multi-round LLM-based multi-agent systems rely on effective communication structures to support collaboration across rounds. However, most existing
arXiv:2605.09104v1 Announce Type: new Abstract: As LLM agents evolve, tokens have emerged as the core economic primitives of Agentic AI. However, their exponential consumption introduces severe comput