Knowledge catalogue
arXiv:2610.09458v1 Announce Type: new Abstract: When an LLM answers a state-specific policy question wrongly, it may be hallucinating, or it may be returning a real value that holds in another state.
I spent the past year independently building Slow Vale, an LLM-driven life simulation. The Chinese server now has 800+ AI residents sharing one continuously running city. This is an engineering write-
arXiv:2610.07835v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) have demonstrated strong capabilities in solving complex problems across diverse domains. Recently, the dynamic orch
arXiv:2610.07470v1 Announce Type: cross Abstract: Combinatorial Thompson sampling (CTS) draws independent posterior samples for every arm, so its exploration dynamics ignore any relation among arms. W
arXiv:2610.08018v1 Announce Type: new Abstract: Reliable tool use requires more than triggering a mechanism or matching a query to an API description. Before selecting a specific tool, an agent must f
arXiv:2610.07570v1 Announce Type: new Abstract: In clinical practice, agreement among independent experts is treated as evidence of reliability, and multi-round consensus has become a core mechanism o
arXiv:2610.06329v1 Announce Type: new Abstract: Modern LLM training increasingly relies on heterogeneous data sources spanning different domains, tasks, preference distributions, and difficulty levels
arXiv:2610.04744v1 Announce Type: new Abstract: When a team of robots delegates planning and mutual trust to LLM agents, a single compromised robot can corrupt the shared outcome. We study this threat
arXiv:2603.23533v3 Announce Type: replace-cross Abstract: Markdown carries structure a parser reads for free: headers, section paths, and block boundaries. Many RAG pipelines also spend LLM calls per
arXiv:2610.04756v1 Announce Type: cross Abstract: Self-evolving large language model (LLM) systems repeatedly propose, evaluate, and incorporate updates to prompts, skills, or other persistent artifac
arXiv:2610.03014v1 Announce Type: cross Abstract: Large language model (LLM)-based agents increasingly connect model-generated decisions to security-sensitive software capabilities such as command exe
arXiv:2610.02762v1 Announce Type: new Abstract: Dynamic LLM routers promise to cut inference costs by sending each query to the cheapest model that can answer it correctly. We analyze six commercial r
arXiv:2610.02516v1 Announce Type: cross Abstract: Zero-shot classifiers are useful for routing user requests to specialized LLM tasks, but scoring every request against a large candidate set is expens
arXiv:2610.00511v1 Announce Type: new Abstract: Before a difficult decision, people often act simply to understand the situation better. We turn an object to see another side, place alternatives next
arXiv:2601.22169v2 Announce Type: replace-cross Abstract: Humans are susceptible to undesirable behaviours and privacy leaks under the influence of alcohol. This paper investigates drunk language, i.e
arXiv:2610.01257v1 Announce Type: cross Abstract: Scientific progress emerges from a longitudinal ecosystem in which researchers, institutions, funding agencies, collaboration networks, and the scient
arXiv:2610.01592v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly applied to process streaming data, with practitioners relying on benchmarks to select the best model eve
arXiv:2603.28005v2 Announce Type: replace Abstract: When an LLM judge only has to assign a three-way support label to a candidate answer given a reference, does asking it to decompose the answer into
arXiv:2609.38585v1 Announce Type: cross Abstract: Existing Large Language Model (LLM) routing methods score LLMs independently to select top-k models. However, this ignores model correlations and enfo
arXiv:2609.39352v1 Announce Type: cross Abstract: LLM agents increasingly rely on reusable Skills for complex, multi-step tasks, creating a critical supply-chain attack surface where poisoned Skill co
arXiv:2609.38672v1 Announce Type: cross Abstract: Beam-search-based test-time methods provide an effective way to improve large language model (LLM) performance on long-horizon generation by pruning i
arXiv:2609.38448v1 Announce Type: new Abstract: Open-ended LLM homogeneity can create false plurality when several systems appear to offer independent perspectives while returning the same familiar de
arXiv:2609.38792v1 Announce Type: new Abstract: We study training LLM judges from natural language feedback, especially for subjective tasks where the verdict depends strongly on which evaluation crit
arXiv:2609.39701v1 Announce Type: new Abstract: Value steering should change an LLM's normative priorities while preserving the scenario, facts, and task constraints underlying its answer. Conventiona
arXiv:2609.38275v1 Announce Type: cross Abstract: Persistent memory helps LLM agents carry information across long interactions, but correct memory can still be used incorrectly when queries change or
arXiv:2609.38816v1 Announce Type: new Abstract: While multi-agent and model collaboration algorithms gain traction to combine the strengths of diverse Large Language Models (LLMs), existing systems re
arXiv:2609.36359v1 Announce Type: new Abstract: Graph-based approximate nearest neighbor search (ANNS) is widely used for large-scale semantic search. Its indices are constructed primarily based on ge
arXiv:2609.37658v1 Announce Type: new Abstract: LLM agents are increasingly expected to support enterprise workflows, where tasks often involve missing information, uncertainty, feedback, and long-ter
arXiv:2602.02848v2 Announce Type: replace Abstract: Advances in large language models have driven strong performance across many tasks, but their memory and compute costs still hinder deployment. SVD-
arXiv:2609.32567v1 Announce Type: new Abstract: LAOD and similar zero-training LLM+open-vocabulary-detector (OVOD) pipelines score two things separately: class-agnostic localization accuracy (CAAP) an
arXiv:2609.35569v1 Announce Type: cross Abstract: Large language model (LLM) serving has environmental impacts across energy consumption, carbon emission, water consumption, and biodiversity loss. Yet
arXiv:2609.34681v1 Announce Type: new Abstract: Learning-rate (LR) scheduling plays a central role in large language model (LLM) pretraining, yet current practice still relies heavily on hand-crafted
arXiv:2609.30341v1 Announce Type: new Abstract: Data Spaces enable sovereign and governed data sharing across organizational boundaries, but their integration with AI agents remains challenging due to
arXiv:2609.30849v1 Announce Type: new Abstract: Prior work has examined the self-consistency of LLM-generated explanations using surface-level perturbation methods. However, the strength of these pert
arXiv:2609.31013v1 Announce Type: new Abstract: Researchers increasingly use generative large language models (LLMs) to convert corporate text into empirical variables. We examine the extent to which
arXiv:2609.30074v1 Announce Type: cross Abstract: Evaluations of LLM systems routinely average over small prompt sets and report models as a ranked table. We ask how much confidence such a table deser
NarrateAI delivers production-ready LLM quality assurance on Amazon Bedrock. This post details five techniques—adaptive pipeline orchestration, cross-account multi-model failover, real-time streaming
arXiv:2609.27953v1 Announce Type: cross Abstract: Some LLM-based recommendation rerankers are evaluated under an oracle protocol that guarantees the ground-truth item is present in the scored set, eit
arXiv:2609.24446v2 Announce Type: cross Abstract: Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subseque
arXiv:2609.22512v1 Announce Type: new Abstract: Consensus among LLM judges is often taken as strong evidence that a decision is correct. This assumes that judges make their errors independently. In pr
arXiv:2609.12551v2 Announce Type: replace-cross Abstract: AI is beginning to make substantive contributions to LLM inference optimization. Existing AI optimizations are predominantly profiling-based.
arXiv:2609.24036v1 Announce Type: new Abstract: This paper presents an LLM-based system that translates natural-language access control policies (NLACPs) into executable Rego code for Open Policy Agen
arXiv:2601.20900v4 Announce Type: replace-cross Abstract: Adapting large language model (LLM)-based automatic speech recognition (ASR) systems to new domains using text-only data is a significant yet
arXiv:2609.22818v1 Announce Type: cross Abstract: Memory-poisoning defenses for LLM agents are typically evaluated by their ability to prevent attacks. However, the traffic they process is rarely adve
arXiv:2609.24631v1 Announce Type: new Abstract: Autonomous parking in nonconvex and narrow environments remains challenging. Although optimal-control methods can explicitly enforce vehicle dynamics an
arXiv:2609.24895v1 Announce Type: new Abstract: When an LLM supplies an argument that a user could not readily construct, how can the user decide whether to accept its claim? Inspired by interactive p
You know the thing where you ask a chatbot what's wrong with your plan and it goes 'there are three problems here' and problem three is clearly the runt of the litter? There's a word for that now. An
arXiv:2609.23264v1 Announce Type: new Abstract: Peer-review evaluation is increasingly being automated with LLM-as-a-judge metrics, but this creates a measurement risk. A review may receive a high sco
arXiv:2609.24979v1 Announce Type: new Abstract: On-device large language models (`LLMs'), e.g. running on mobile phones, are ripe for improvement via personalization. The limited compute resources of
arXiv:2601.03981v3 Announce Type: replace Abstract: To efficiently combat the spread of LLM-generated misinformation in the news domain, we present RADAR, a Retrieval-Augmented Detector with Adversari
arXiv:2609.24464v1 Announce Type: new Abstract: Using a Large Language Model (LLM) as the clusterer at production scale is hard: prompts cannot hold the entire label space, and per-document serial pro
Sometimes everybody is right! Me, spring 2023 onwards: giving LLM-driven agents unrestricted internet access with read/write permissions is going to be a security nightmare. The AI industry: Agents ar
arXiv:2602.03128v2 Announce Type: replace Abstract: Multi-agent LLM frameworks are data-intensive systems that govern how agents orchestrate tasks, manage state, and coordinate decisions. These archit
NVIDIA AIPerf is a benchmarking framework that supersedes GenAI‑Perf with a multiprocess architecture, eliminating client‑side bottlenecks during high‑concurrency LLM testing. It supports more than 15
arXiv:2605.13481v2 Announce Type: replace Abstract: We introduce PersonalAI 2.0 (PAI-2), a novel framework designed to enhance LLM-based systems through integration of external knowledge graphs (KGs).
arXiv:2609.19883v1 Announce Type: cross Abstract: Characterizing LLM reasoning remains an open challenge, as many existing benchmarks isolate specific reasoning skills, rely on external knowledge, or
arXiv:2609.18123v1 Announce Type: new Abstract: Large language model agents tune GPU kernels and serving engines through a closed loop of propose, measure, and keep, but the measurements behind this l
arXiv:2609.17695v1 Announce Type: new Abstract: A large language model (LLM) agent can follow more graph paths without acquiring more independent evidence. GraphEcho tests whether agents mistake these
Things to try with Jev right now: 1. LLM-as-a-Judge evaluation 2. Routing for agent harnesses harness 3. Scaling agent orchestration by enabling smarter subagent creation with SOTA classification capa
arXiv:2609.16206v1 Announce Type: new Abstract: Disaggregated LLM serving places compute heavy prefill and memory heavy decode on separate GPU pools. Systems such as DistServe, Splitwise, and Mooncake