Knowledge catalogue
arXiv:2609.37062v1 Announce Type: cross Abstract: Dynamic layer skipping reduces LLM computation by allowing each token to execute only a subset of the model's layers. However, existing skippers rely
arXiv:2609.31877v1 Announce Type: cross Abstract: Cloud-based Large language model (LLM) services create a network-level traffic side channel that can expose model, prompt, and task behavior despite e
arXiv:2609.34679v1 Announce Type: new Abstract: Bipartite matching is a fundamental problem in game theory and market design. Classical approaches such as Gale--Shapley assume complete preferences and
arXiv:2609.31395v1 Announce Type: cross Abstract: Agentic LLM inference accumulates long KV caches across iterative observation-reasoning-action loops, imposing substantial memory overhead and limitin
arXiv:2609.31540v1 Announce Type: cross Abstract: Sending every network-automation input to a third-party frontier LLM exports sensitive artifacts such as production configurations, topologies, and lo
arXiv:2609.30662v1 Announce Type: new Abstract: Large language models (LLMs) can plan, use tools, write code, and execute long-horizon workflows, yet strong local competence does not guarantee project
Apple Silicon Macs on macOS 26+ come with a small LLM built in. No download, no API key, and nothing leaves your Mac. Why I built it I was making a tool that writes API docs from code, and I didn't wa
arXiv:2609.31468v1 Announce Type: cross Abstract: LLMs increasingly act as purchasing agents, which makes the LLM, not the user, the one choosing among the options that satisfy a request; its preferen
I tested Jev and five LLM judges across ten Arize Phoenix evaluators to measure how often their answers changed alongside accuracy, cost, and latency. The post What Jev’s probabilities reveal that rep
arXiv:2609.26926v1 Announce Type: cross Abstract: Large-scale text annotation brings expert insight to millions of documents, often through a codebook that AI annotators follow. Developing a robust co
arXiv:2609.27606v1 Announce Type: new Abstract: We introduce State-Grounded Conditioning (SGC), a design principle for user-facing LLM agents that must condition on live user state (game state, sessio
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:2609.22218v1 Announce Type: cross Abstract: As LLM agents are exposed to hundreds to tens of thousands of skills, tools, and API functions, full-library prompting becomes costly, slow, and less
arXiv:2510.25595v2 Announce Type: replace-cross Abstract: While Large Language Model (LLM) agents are often approached from the angle of action planning/generation to accomplish a goal (e.g., given by
arXiv:2609.19657v1 Announce Type: cross Abstract: Repeated prompt prefixes are increasingly common in LLM serving workloads, appearing in system prompts, templated retrieval-augmented generation pipel
arXiv:2609.19866v1 Announce Type: new Abstract: High annotation reproducibility does not necessarily imply that an LLM-inferred measure captures the construct it is intended to measure. We test this d
arXiv:2609.18204v1 Announce Type: cross Abstract: Organizations increasingly use oversight loops where one large language model (LLM) audits another's outputs alongside procedural traces of claimed st
arXiv:2609.17549v1 Announce Type: new Abstract: Cyberbullying (CB) is a complex social phenomenon characterized by repeated aggression, power imbalance, and multi-party interaction. Although large lan
arXiv:2608.28363v2 Announce Type: replace Abstract: LLM agents increasingly modify their own prompts, tools, middleware, resources, and execution harnesses at runtime. Such self-evolution can improve
arXiv:2609.18346v1 Announce Type: new Abstract: Large language models (LLM) deployed as autonomous pricing agents may sustain supracompetitive prices through tacit coordination. We develop a causal gr
arXiv:2609.18112v1 Announce Type: cross Abstract: LLM serving is typically offered as a shared, multi-tenant service, where high-demand workloads from one client can cause latency SLO violations for o
arXiv:2609.17008v1 Announce Type: new Abstract: Large language model (LLM) inference is often constrained by both computation and memory, especially in offloading-based deployments where model weights
arXiv:2609.14987v1 Announce Type: cross Abstract: Large language model (LLM) agents interact with external environments through tool invocation, but tool outputs can also expose them to indirect promp
arXiv:2609.14060v1 Announce Type: cross Abstract: Quantization is one of the default deployment paths for open-weight LLM agents, but it is not behavior-preserving: an adversary can release a full-pre
arXiv:2609.14399v1 Announce Type: new Abstract: Natural language prompts and skills serve as the strategic backbone of LLM-based agents. Recent advances in prompt and skill optimization have achieved
arXiv:2609.14773v1 Announce Type: new Abstract: As LLM conversations grow to hundreds of turns, full-context injection incurs O(N^2) cumulative token costs, while lossy summarization or hard truncatio
arXiv:2609.14565v1 Announce Type: new Abstract: LLM-based sequential recommenders usually cast next-item prediction as text generation, but this interface is poorly matched to full-catalog top-K ranki
arXiv:2609.13436v1 Announce Type: new Abstract: Large Language Model (LLM) agents offer a promising path toward autonomously managing long-term physical tasks without human intervention. However, phys
arXiv:2609.15309v1 Announce Type: new Abstract: Large language model (LLM) agents allocate test-time compute adaptively as they revise solutions, use tools, explore alternatives, and decide when to st
arXiv:2609.11452v1 Announce Type: new Abstract: Efficient routing optimization is essential to freight transportation, urban logistics, and shared mobility, where high-quality heuristics are often req
arXiv:2609.10790v1 Announce Type: cross Abstract: We present a Kubernetes Dynamic Resource Allocation (DRA) driver that makes composable CXL memory a schedulable cluster resource, and evaluate the res
arXiv:2609.10892v1 Announce Type: cross Abstract: When an indirect prompt injection succeeds against an LLM agent, the compromise is visible in the agent's own behavior: a benign prefix of tool calls,
arXiv:2609.08256v1 Announce Type: cross Abstract: Automated red-team attacks and blue-team defenses for large language models (LLMs) are advancing quickly. However, attackers and defenders are built a
arXiv:2606.16723v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly take actions (screening applicants, recommending credit, triaging patients), yet fairness for LLMs is
arXiv:2609.08765v1 Announce Type: cross Abstract: Large language model (LLM) benchmarks are often treated as fixed datasets with stable scores, yet their outcomes depend on configurable evaluation pip
arXiv:2609.08566v1 Announce Type: new Abstract: KV cache is evolving from a serving optimization into an external memory substrate for long-term LLM agents. In a shared multi-user deployment, however,
Amazon SageMaker Inference now offers prefix-aware routing, a routing strategy that sends requests sharing the same prompt prefix to the same instance so the KV cache stays warm. In benchmarks on Llam
arXiv:2609.05441v1 Announce Type: new Abstract: Long-term memory for LLM agents is evaluated today by conversational recall benchmarks (LoCoMo, LongMemEval), which measure question answering over dial
Great paper on designing multi-agent systems. How many distinct communication topologies does an LLM multi-agent system actually need? This works claims that it's about six. Technical summary: Researc
arXiv:2609.03494v1 Announce Type: new Abstract: Long-output reasoning has made the key--value (KV) cache a critical memory bottleneck for efficient LLM serving. Existing KV compression methods usually
arXiv:2609.03383v1 Announce Type: new Abstract: Graph-based policy optimization improves credit assignment for long-horizon LLM agents by organizing rollout trajectories into state-transition graphs.
arXiv:2601.07468v2 Announce Type: replace Abstract: Memory enables Large Language Model (LLM) agents to perceive, store, and use information from past dialogues, which is essential for personalization
arXiv:2609.02092v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) are increasingly considered for high-stakes decision-making, yet outcome-based fairness audits can miss where risks
arXiv:2609.01660v1 Announce Type: cross Abstract: Production deployments of large language model (LLM) agents remain unreliable on long, multi-step workflows even as benchmark success rates climb stea
arXiv:2607.10103v2 Announce Type: replace-cross Abstract: As large language models (LLMs) become widely deployed, their outputs can be copied, transformed, and redistributed at scale without reliable
arXiv:2609.00608v1 Announce Type: new Abstract: LLM-based user simulators are increasingly used to evaluate autonomous agents at scale, in place of costly human evaluations. Despite this promise, thes
arXiv:2609.01337v1 Announce Type: new Abstract: LLM-based forecasting systems have improved on real-world tasks such as financial markets and sports outcomes, largely through stronger search and tool
arXiv:2609.01073v1 Announce Type: new Abstract: The LLM-as-a-judge (LLMaJ) framework offers a cost-effective and reproducible solution for automatic evaluation. However, current evaluation practices t
arXiv:2609.00859v1 Announce Type: new Abstract: Vehicle Routing Problems (VRPs) are fundamental combinatorial optimization problems with widespread applications in various scenarios. The advanced opti
arXiv:2609.01035v1 Announce Type: new Abstract: Recursive LLM agents can broaden their search by spawning specialists. Some branches later request tools that send data or deploy code. When should a br
arXiv:2609.00455v1 Announce Type: new Abstract: Large language models (LLMs) are being used as policies for autonomous decision-making and planning in many domains. Despite their strong reasoning capa
arXiv:2608.29606v1 Announce Type: new Abstract: Large language model (LLM) agents need durable, faithful memory of everything a user or organization has said and stored, yet most memory systems commit
arXiv:2608.30373v1 Announce Type: new Abstract: Multi-Agent Debate (MAD) has been widely adopted to improve LLM-based evaluation by prompting multiple agents to negotiate and reach a consensus. Howeve
arXiv:2608.30333v1 Announce Type: cross Abstract: Next-basket repurchase recommendation is commonly formulated as a ranking task: given a customer's purchase history, the system ranks previously purch
arXiv:2608.30543v1 Announce Type: new Abstract: Large Language Models (LLMs) offer new possibilities for scaling qualitative analysis, but existing applications often provide limited methodological tr
arXiv:2608.29856v1 Announce Type: new Abstract: Large language models are increasingly used as scalable evaluators for open-ended tasks. However, many LLM judges derive query-specific criteria during
arXiv:2608.29579v1 Announce Type: new Abstract: Chaotic time series forecasting is a challenging task due to its sensitivity to initial conditions and long-term unpredictability. Traditional methods t
arXiv:2605.05726v2 Announce Type: replace Abstract: As LLM agents are increasingly deployed with large libraries of reusable skills, selecting the right skill for a user request has become a critical
arXiv:2603.04191v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly serving as personal assistants, where users may share individual preferences over extended interaction
arXiv:2608.30362v1 Announce Type: new Abstract: As LLM agents take real-world actions through tools, indirect prompt injection (IPI) has emerged as a serious threat. The standard metric, Attack Succes