Knowledge catalogue
The most important part of an AI agent isn't the LLM. It's what surrounds it. 👇 The first image made it click for me. While exploring LangChain Deep Agents, I ran the same prompt. Same model. Almost t
arXiv:2606.20023v2 Announce Type: replace-cross Abstract: As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, pri
arXiv:2607.06461v1 Announce Type: cross Abstract: While recent Large Language Model (LLM)-based Text-to-Speech (TTS) systems have achieved remarkable naturalness, they predominantly rely on implicit e
arXiv:2607.04293v1 Announce Type: cross Abstract: Building AI Scientist agents with Large Language Models (LLMs) has recently attracted growing attention. Since scientific discovery fundamentally reli
arXiv:2607.04108v1 Announce Type: new Abstract: Large language models are increasingly used as evolutionary engines for scientific discovery: generate candidates, select winners, feed them back as par
If you're struggling to get started with evals, you're not alone. This post explains how to write LLM evals as ordinary tests in CI with Phoenix, pytest, and Vitest/Jest. The post Evals in CI: How to
arXiv:2501.08579v3 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diverse domains. However, our position is that current
arXiv:2607.03441v1 Announce Type: cross Abstract: LLM agents often degrade over long episodes: as trajectories grow, they revisit explored states, repeat failed actions, and lose strategies that previ
arXiv:2607.04576v1 Announce Type: new Abstract: LLM agents increasingly answer questions against knowledge bases they help maintain. A common intuition holds that progressive disclosure, a compact cat
This is what latency optimization looks like below the API 👇 Together ATLAS, NVIDIA Blackwell, CUDA, TensorRT-LLM, Dynamo, and custom kernels all working together to make inference faster for users. P
arXiv:2607.05029v1 Announce Type: cross Abstract: Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage informati
arXiv:2607.01585v1 Announce Type: cross Abstract: Predicate invention (PI), the creation of new predicates to extend the hypothesis space, remains a critical bottleneck in Inductive Logic Programming
arXiv:2607.02255v1 Announce Type: new Abstract: Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see. The simplest contract appends past observations, to
arXiv:2607.01646v1 Announce Type: new Abstract: State-of-the-art large language model (LLM) training takes tens of thousands of graphics processing units (GPUs) for months and encounters failures acro
arXiv:2510.14331v3 Announce Type: replace Abstract: We study program-learning methods that are efficient in both samples and computation. Classical learning theory suggests that when the target admits
arXiv:2607.01240v1 Announce Type: cross Abstract: Count-based F1 is widely used as a proxy for LLM error-detection quality, but this paper shows that it can rise dramatically without a corresponding i
arXiv:2607.01903v1 Announce Type: new Abstract: LLM-integrated applications blend natural language prompts with program code, and much of their runtime behavior originates in the prompt layer rather t
arXiv:2607.02368v1 Announce Type: cross Abstract: Evaluations of LLM personas via psychometric questionnaires typically rely on aggregate scores, discarding within-instance correlation structure. We t
arXiv:2607.00937v1 Announce Type: new Abstract: Persona-driven generations (PDGs) have seen prolific use in research and industry applications, where a large language model (LLM) takes on a 'persona'
arXiv:2606.31371v1 Announce Type: cross Abstract: When large language model (LLM) agents adapt their behavior through evaluator feedback, systematic evaluator biases propagate into the agent's learned
arXiv:2606.30689v1 Announce Type: cross Abstract: Spec-Driven Development (SDD) frameworks guide Large Language Model (LLM)-powered code generation through formal specifications, yet they differ funda
arXiv:2602.06625v2 Announce Type: replace Abstract: Existing LLM-as-a-Judge systems suffer from three fundamental limitations: limited adaptivity to task- and domain-specific evaluation criteria, syst
arXiv:2606.32025v1 Announce Type: new Abstract: Recent LLM agents benefit from skills for solving complex tasks. Skills encapsulate modular packages of procedural knowledge and instructions for perfor
arXiv:2603.14732v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly considered for automated assessment and feedback, understanding when LLM marking is valid is
arXiv:2606.31073v1 Announce Type: new Abstract: Large language models (LLMs) provide a promising interface for high-level robotic task planning, but their use in multi-UAV collaboration remains diffic
arXiv:2606.29771v1 Announce Type: new Abstract: LLM agents are increasingly cast as autonomous portfolio managers, and benchmarks have moved from financial question-answering to sequential trading. Ye
arXiv:2606.30454v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as agents in simulations of social systems, yet it remains unclear when their behavior can be inter
arXiv:2606.29223v1 Announce Type: new Abstract: Autoregressive LLM decoding evaluates every generated token through the full layer stack, even though many tokens become predictable at intermediate dep
arXiv:2606.30219v1 Announce Type: new Abstract: LLM evaluation and AI safety face a shared measurement problem: benchmark scores, reward-model signals, and reported safety metrics can improve while th
arXiv:2507.05257v4 Announce Type: replace-cross Abstract: Recent benchmarks for Large Language Model (LLM) agents primarily focus on evaluating reasoning, planning, and execution capabilities, while a
arXiv:2606.22528v2 Announce Type: replace Abstract: Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget. We show t
arXiv:2606.28363v1 Announce Type: cross Abstract: Objective: To describe the architecture and design rationale of meta-pipe, an open-source large language model (LLM)-agent pipeline that integrates th
arXiv:2606.29013v1 Announce Type: new Abstract: Leveraging capabilities of large language models (LLMs) in text-to-image (T2I) synthesis is an important research direction. In this work we investigate
arXiv:2606.29178v1 Announce Type: new Abstract: When does retention matter for memory-augmented LLM agents? We study this with TraceRetain, a lightweight framework for bounded external memory in froze
arXiv:2606.29567v1 Announce Type: cross Abstract: LLM-based assistants transmit user queries verbatim to third-party API endpoints that lie outside the user's audit or control. When those queries cont
arXiv:2606.29460v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly embedded in social robots to support natural group interactions, yet their role in complex multi-party set
arXiv:2606.29632v1 Announce Type: cross Abstract: Audio-Visual Speech Recognition takes two input modalities, acoustic and visual streams, where visual information from lip movements aids recognition
arXiv:2606.28376v1 Announce Type: cross Abstract: Long-horizon large language model (LLM) agents accumulate interaction trajectories that quickly exceed any practical prompt budget, and existing memor
arXiv:2510.16492v4 Announce Type: replace Abstract: As Large Language Model (LLM) agents increasingly operate in complex environments with real-world consequences, their safety becomes critical. While
arXiv:2606.20014v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments rem
LLM-as-a-Judge explained in ~10 mins. Knowing how to build AI verifiers and judges is one of the most important emerging AI skills today. Here is a quick intro on the topic and where to learn how to a
In this post, we show you how PAR built a production-ready multi-tenant LLM analytics system that enforces row-level security through a three-layer architecture: cryptographic request signing with AWS
arXiv:2606.27632v1 Announce Type: new Abstract: As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We arg
arXiv:2606.27009v1 Announce Type: new Abstract: Multi-agent large language model (LLM) loops, for example a Writer that drafts and a Critic that revises, are almost always terminated by a fixed iterat
arXiv:2606.26130v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used to guide research methodology, yet their default methodological tendencies under minimal prompting
arXiv:2602.02219v2 Announce Type: replace Abstract: Large language models are widely employed as evaluators, a paradigm commonly referred to as LLM-as-a-judge. Prior research has predominantly examine
arXiv:2606.14581v2 Announce Type: replace Abstract: Granting LLMs direct control over costly, irreversible scientific experiments leads to unsafe exploration and unstable performance, but discarding L
arXiv:2606.24420v1 Announce Type: new Abstract: In high-stakes document processing pipelines, including financial reconciliation, compliance verification, and procurement automation, an LLM extraction
arXiv:2606.24467v1 Announce Type: new Abstract: Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiti
arXiv:2606.24163v1 Announce Type: cross Abstract: Reliable provenance for LLM outputs requires multi-bit watermarks that remain robust under editing while maintaining strict false-positive control. Ex
arXiv:2606.24506v1 Announce Type: cross Abstract: Emerging LLM services increasingly host many sparse MoE models, yet most models receive sparse requests and remain cold. This creates a GPU memory pro
arXiv:2606.23915v1 Announce Type: new Abstract: Practice often treats automatic metrics for attribution in LLM retrieval-augmented generation as interchangeable. We audit eight automatic scorers -- le
arXiv:2606.24133v1 Announce Type: cross Abstract: The composition of training data, governed by the diversity of sources and their mixing strategy, is a cornerstone of Large Language Model (LLM) pre-t
arXiv:2603.20450v2 Announce Type: replace-cross Abstract: A number of scientific conferences and journals have recently enacted policies that prohibit LLM usage by peer reviewers, except for polishing
arXiv:2603.16131v2 Announce Type: replace Abstract: The explosive growth of AI research has created unprecedented information overload, increasing the demand for scientific summarization at multiple l
arXiv:2606.23391v1 Announce Type: new Abstract: Time series forecasting is a fundamental machine learning task. Recent work has explored Large Language Models (LLMs) for this purpose due to their stro
arXiv:2606.23370v1 Announce Type: cross Abstract: Device-side Large Language Models (LLMs) have grown explosively, offering stronger privacy and higher availability than their cloud-side counterparts.
arXiv:2606.22741v1 Announce Type: new Abstract: Can one graph represent every kind of LLM agent's run? A trace records what each step did, never what it relied on, the state it read, and the results i
arXiv:2606.23104v1 Announce Type: new Abstract: On-policy distillation (OPD) improves LLM reasoning by training a student model on its own generated outputs, but standard OPD treats all student-genera
arXiv:2606.20629v1 Announce Type: cross Abstract: LLM agents are increasingly deployed as multi-role teams, where tasks are divided across specialized roles such as planner, executor, and verifier. In