Knowledge catalogue
arXiv:2503.06047v2 Announce Type: replace Abstract: Large language model (LLM)-based agents are increasingly applied to complex strategic environments that demand long-horizon reasoning, multi-agent i
arXiv:2605.09735v1 Announce Type: cross Abstract: Static-graph LLM decoders provide predictable launches, fixed tensor shapes, and low submission overhead, but online decoding exposes highly irregular
arXiv:2605.10779v1 Announce Type: cross Abstract: The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content s
arXiv:2605.09918v1 Announce Type: cross Abstract: Reconciling platform revenue with user experience in LLM advertising motivates a data-centric foundation. We introduce NaiAD, the first comprehensive
arXiv:2605.09863v1 Announce Type: cross Abstract: Production LLM coding agents drift over long sessions: they forget user-specified constraints, slip into mistakes the user already flagged, and confab
arXiv:2605.08680v1 Announce Type: cross Abstract: LLM code-generation pipelines often sample multiple candidates and select one final answer without access to a complete oracle. Existing pipelines mix
arXiv:2605.08693v1 Announce Type: new Abstract: Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and selec
arXiv:2603.06859v2 Announce Type: replace-cross Abstract: Removing an agent from a cooperative team to measure its contribution seems natural, yet in multi-agent LLM systems this evaluation distorts t
arXiv:2605.06716v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents have fundamentally reshaped artificial intelligence by integrating external tools and planning capabilities. Whi
arXiv:2605.07301v1 Announce Type: new Abstract: Accurately predicting opponents' behavior from interactions is a fundamental capability for large language model (LLM)-based agents in multi-agent and g
arXiv:2605.04418v1 Announce Type: new Abstract: The empirical success of large language model (LLM) pre-training relies heavily on heuristic stabilization techniques, such as explicit normalization la
Release: llm-gemini 0.31 gemini-3.1-flash-lite is no longer a preview. Here's my write-up of the Gemini 3.1 Flash-Lite Preview model back in March. I don't believe this new non-preview model has chang
arXiv:2605.05175v1 Announce Type: cross Abstract: Background: Existing MRI LLM benchmarks rely mainly on review-book multiple-choice questions, where top proprietary models already score highly, limit
arXiv:2605.01100v1 Announce Type: new Abstract: This work presents a knowledge-driven decision-support system that integrates structured defect knowledge with LLM-based reasoning to provide explainabl
arXiv:2605.00831v1 Announce Type: cross Abstract: The rise of million-token, agent-based applications has placed unprecedented demands on large language model (LLM) inference services. The long-runnin
arXiv:2603.26845v2 Announce Type: replace-cross Abstract: Most LLM-driven GIS assistants solve narrow single-step tasks tightly coupled to proprietary platforms such as ArcGIS or QGIS, limiting their
arXiv:2601.21972v4 Announce Type: replace Abstract: Recent work has explored optimizing LLM collaboration through Multi-Agent Reinforcement Learning (MARL). However, most MARL fine-tuning approaches r
arXiv:2605.03299v1 Announce Type: new Abstract: Cross-lingual topic modeling aims to discover shared semantic structures across languages, yet existing models depend on sparse bilingual resources and
arXiv:2605.01280v1 Announce Type: cross Abstract: This position paper argues that LLM inference serving has outgrown generic heuristics and now demands mathematical optimization and algorithmic founda
arXiv:2502.04419v3 Announce Type: replace-cross Abstract: Generating synthetic datasets via large language models (LLMs) has emerged as a promising approach to improve LLM performance. However, LLMs i
arXiv:2605.02187v1 Announce Type: cross Abstract: Bring-Your-Own-Key (BYOK) agent architectures let users route LLM traffic through third-party relays, creating a critical integrity gap: a malicious r
arXiv:2605.00254v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) architectures have turned LLM serving into a cluster-scale workload in which communication consumes a considerable portion of
arXiv:2605.02862v1 Announce Type: new Abstract: The integration of Large Language Model (LLM) reasoning principles into classical robot path planning represents a rapidly emerging research direction.
arXiv:2510.13668v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) inference has emerged as a fundamental paradigm, however, variations in output length cause severe workload imbalan
arXiv:2605.00087v1 Announce Type: cross Abstract: Many recent news reports have claimed that content generated by large language models (LLMs) is taking over the web. However, these claims are typical
arXiv:2510.17281v5 Announce Type: replace Abstract: Scaling up data, parameters, and test-time computation has been the mainstream methods to improve LLM systems (LLMsys), but their upper bounds are a
arXiv:2604.09718v2 Announce Type: cross Abstract: LLM-driven web agents operating through continuous inference loops -- repeatedly querying a model to evaluate browser state and select actions -- exhi
arXiv:2604.27789v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used as core dependencies in software systems. However, the hosted LLM services evolve continuously thro
arXiv:2604.27082v1 Announce Type: new Abstract: We present a framework for migrating production Large Language Model (LLM) based systems when the underlying model reaches end-of-life or requires repla
arXiv:2508.16131v2 Announce Type: replace-cross Abstract: Code completion entails the task of providing missing tokens given a surrounding context. It can boost developer productivity while providing
arXiv:2604.25456v1 Announce Type: new Abstract: We investigate linguistic biases in LLM-based restaurant and product recommendations given prompts varying across Southern American English (AE), Indian
arXiv:2603.21362v2 Announce Type: replace Abstract: LLM-as-Judge evaluation fails agent tasks because a fixed rubric cannot capture what matters for this task: code debugging demands Correctness and E
arXiv:2603.21357v3 Announce Type: replace Abstract: LLM agents fail on the majority of real-world tasks -- GPT-4o succeeds on fewer than 15% of WebArena navigation tasks and below 55% pass@1 on ToolBe
arXiv:2508.08127v2 Announce Type: replace Abstract: The security of LLM-based multi-agent systems (MAS) is critically threatened by propagation vulnerability, where malicious agents can distort collec
arXiv:2604.23345v1 Announce Type: new Abstract: Cross-domain task-oriented dialogue requires reasoning over implicit and explicit feasibility constraints while planning long-horizon, multi-turn action
arXiv:2604.23270v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However,
arXiv:2510.22609v2 Announce Type: replace Abstract: Accurate symptom-to-disease classification and clinically grounded treatment recommendations remain challenging, particularly in heterogeneous patie
arXiv:2604.23902v1 Announce Type: new Abstract: Traffic signal control is a critical task in intelligent transportation systems, yet conventional fixed-time and rule-based methods often struggle to ad
arXiv:2604.23333v1 Announce Type: cross Abstract: Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability
arXiv:2604.22755v1 Announce Type: cross Abstract: Reliable decision support in nuclear engineering requires traceable, domain-grounded knowledge retrieval, yet safety and risk analysis workflows remai
When an LLM acts happy (“EUREKA!”) or sad (“I have failed…”), is that meaningless mimicry, or does it reflect something “real”? We don’t know if LLMs are conscious. But they increasingly seem to exhib
arXiv:2604.22520v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable performance in Machine Translation (MT), but deploying them at scale remains prohibitively expensi
arXiv:2604.21584v1 Announce Type: new Abstract: Feature discovery from complex unstructured data is fundamentally a reasoning problem: it requires identifying abstractions that are predictive of a tar
arXiv:2503.16416v2 Announce Type: replace Abstract: LLM-based agents represent a paradigm shift in AI, enabling autonomous systems to plan, reason, and use tools while interacting with dynamic environ
arXiv:2604.20732v1 Announce Type: cross Abstract: Freight brokerages negotiate thousands of carrier rates daily under dynamic pricing conditions where models frequently revise targets mid-conversation
arXiv:2604.20021v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become increasingly popular, caching responses so that they can be reused by users with semantically similar queries h
arXiv:2508.16676v2 Announce Type: replace-cross Abstract: Transformer architecture gradually dominates the LLM field. Recent advances in training optimization for Transformer-based large language mode
arXiv:2601.04562v2 Announce Type: replace Abstract: Generative recommendation with large language models (LLMs) reframes prediction as sequence generation, yet existing LLM-based recommenders remain l
arXiv:2604.19157v1 Announce Type: new Abstract: KV-cache memory is a major bottleneck in real-world LLM serving, where systems must simultaneously support latency-sensitive small-batch requests and hi
arXiv:2604.18607v1 Announce Type: cross Abstract: LLM-driven program evolution can discover high-quality programs, but its cost and run-to-run variance hinder reliable progress. We propose TurboEvolve
arXiv:2604.17249v1 Announce Type: cross Abstract: Rowhammer on GPU DRAM has enabled adversarial bit flips in model weights; shared KV-cache blocks in LLM serving systems present an analogous but previ
arXiv:2508.14913v4 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated significant capabilities in solving mathematical problems expressed in natural language. However, mul
arXiv:2510.11251v2 Announce Type: replace-cross Abstract: The proliferation of open-source code and large language models (LLMs) for code generation has amplified the risks of unauthorized reuse and i
arXiv:2506.02718v2 Announce Type: replace Abstract: Large language models (LLMs) are versatile, yet their deployment in complex real-world settings is limited by static knowledge cutoffs and the diffi
arXiv:2601.11886v2 Announce Type: replace Abstract: In high-stakes domains like medicine, it may be generally desirable for models to faithfully adhere to the context provided. But what happens if the
arXiv:2604.17271v1 Announce Type: new Abstract: Node classification on text-attributed graphs (TAGs) is a fundamental task with broad applications in citation analysis, social networks, and recommenda
arXiv:2509.23542v2 Announce Type: replace Abstract: The LLM-as-a-judge paradigm is widely used in both evaluating free-text model responses and reward modeling for model alignment and fine-tuning. Rec
arXiv:2604.18396v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated exceptional performance across diverse domains but are increasingly constrained by high inference latency
arXiv:2604.16511v1 Announce Type: cross Abstract: We present SQL Query Engine, an open-source, self-hosted service that translates natural language questions into validated PostgreSQL queries through
arXiv:2604.15840v1 Announce Type: new Abstract: Reinforcement learning for LLM agents is typically conducted on a static data distribution, which fails to adapt to the agent's evolving behavior and le