Knowledge catalogue
arXiv:2609.32961v1 Announce Type: new Abstract: As LLM agents tackle longer tasks, they increasingly compress growing histories of reasoning, actions, and tool outputs. Compression can reduce token us
arXiv:2607.17568v2 Announce Type: replace Abstract: Resource-constrained deployment requires sustaining large language model (LLM) capabilities as models scale under fixed memory and computation budge
arXiv:2609.33768v1 Announce Type: new Abstract: Multi-agent systems (MAS) have recently emerged as an effective approach for coordinating large language model (LLM)-based agents to solve complex tasks
arXiv:2609.33536v1 Announce Type: new Abstract: Large language model (LLM) serving is increasingly constrained by the GPU memory consumed by key-value (KV) caches. Existing compression, eviction, and
arXiv:2609.35426v1 Announce Type: new Abstract: Reinforcement Learning-based post-training of Large Language Models (LLM) has been successfully applied to improve their reasoning capabilities. Existin
arXiv:2609.33038v1 Announce Type: cross Abstract: We propose DAST (Diversifying Arithmetic Sampling with TokenTour), a method that increases the diversity of LLM outputs without any change to the marg
arXiv:2609.34064v1 Announce Type: new Abstract: Reinforcement learning (RL) has become an effective post-training paradigm for long-horizon large language model (LLM) agents. However, we find that the
arXiv:2511.18038v2 Announce Type: replace-cross Abstract: Testing RESTful API is increasingly complicated but indispensable to quality assurance of cloud-native applications. This paper reports a mult
arXiv:2609.32379v1 Announce Type: new Abstract: What controls are needed to interpret execution performance and audit scores in LLM agent evaluations? We study two limits on these interpretations in a
arXiv:2609.35701v1 Announce Type: new Abstract: The success of large language models (LLMs) has been accompanied by continued growth in model size and pretraining costs. Muon offers high accuracy and
arXiv:2609.34555v1 Announce Type: new Abstract: Long-context LLM serving is increasingly bottlenecked by decode, where large KV caches limit batch size and underutilize GPUs. Sparse KV cache offloadin
arXiv:2609.34287v1 Announce Type: cross Abstract: LLM pretraining corpora are normally cleaned by a stack of hand-written heuristics. A heuristic scraper extracts the main content from HTML, and dozen
arXiv:2609.34215v1 Announce Type: cross Abstract: Evaluating how LLM agents recover from mid-task failures is central to deploying reliable agentic systems. Existing checkpoint-based benchmarks measur
arXiv:2609.34228v1 Announce Type: new Abstract: Evaluating statistical discovery by large language model (LLM) agents requires verifiable analytical ground truth. Establishing such ground truth for re
arXiv:2609.34370v1 Announce Type: new Abstract: Spexis is a multi-GPU LLM inference framework that improves the efficiency of pipeline and tensor parallelism through speculative parallelism. Rather th
arXiv:2609.35065v1 Announce Type: cross Abstract: Reusable prefix key-value (KV) caches can outgrow GPU memory in large language model (LLM) serving. A memory-semantic flash hierarchy offers SSD-backe
arXiv:2609.31900v1 Announce Type: new Abstract: Modern LLM post-training composes supervised fine-tuning (SFT), reinforcement learning with verifiable rewards (RLVR), and on-policy distillation (OPD)
arXiv:2609.30751v1 Announce Type: new Abstract: Pairwise language-model judges can gather evidence through direct comparison, reasoning, or reference-based verification, but no single protocol is best
arXiv:2609.30492v1 Announce Type: cross Abstract: Language models often produce homogeneous responses to open-ended tasks; such homogeneity can spawn groupthink-the convergence of ideas toward a singu
arXiv:2609.30523v1 Announce Type: new Abstract: Large language model (LLM)-powered multi-robot systems are vulnerable to semantic manipulation: an accepted false world-state claim can trigger a fleet-
arXiv:2609.30360v1 Announce Type: cross Abstract: Inspired by the problem of identifying the best model from a collection of large language models (LLMs) with heterogeneous querying costs, we formulat
arXiv:2609.30882v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to assess long-form medical videos, but their effectiveness may depend on whether transcripts are pro
arXiv:2609.31071v1 Announce Type: new Abstract: Corr2Cause asks whether a causal claim holds in every DAG compatible with observed correlations and conditional independencies. We frame this as latent-
arXiv:2609.30797v1 Announce Type: new Abstract: Text-based memory and context compression support reuse of past interactions. Resizing continuous memory changes the input to a frozen LLM, coupling cap
arXiv:2609.30439v1 Announce Type: new Abstract: We introduce target-speaker unlearning ASR (TSU-ASR) task in a fully end-to-end framework for multi-speaker ASR and diarization. Given a multi-speaker u
arXiv:2609.30289v1 Announce Type: new Abstract: In team collaboration scenarios, memory is heterogeneous and continually evolving. Team memories capture collective decisions, protocols, and current co
arXiv:2609.29773v1 Announce Type: new Abstract: Many real-world tasks (e.g., office workflows, scientific experimentation) require LLM agents to interact repeatedly with their environments for context
arXiv:2609.29807v1 Announce Type: new Abstract: A large language model (LLM) can turn a text into a distribution over an ordered scale, but that distribution is a noisy measurement: saturated, compres
arXiv:2609.29016v1 Announce Type: cross Abstract: AI-driven scientific discovery accelerates research by autonomously developing solutions and designs. Large language model (LLM) agents support this p
arXiv:2609.28876v1 Announce Type: new Abstract: We introduce Forecast-Dojo, a replayable environment for benchmarking and training LLM forecasting agents. It combines resolved prediction-market questi
arXiv:2609.29015v1 Announce Type: new Abstract: Decentralized LLM-based multi-agent systems coordinate through local interactions, but an agent can remain responsive while its task-solving quality per
arXiv:2609.28585v1 Announce Type: cross Abstract: Multi-step tool-calling LLM agents rely on host runtimes to preserve state across turns. When a runtime carries an external tool return into later mod
arXiv:2609.28693v1 Announce Type: new Abstract: Large Language Model (LLM) agents struggle to scale safely when exposed to vast enterprise toolsets. Providing an agent with access to every internal to
arXiv:2609.29935v1 Announce Type: cross Abstract: We study the detection of LLM-generated text under editing and contamination. Modeling human and machine text as finite-order Markov processes with Hu
arXiv:2609.29709v1 Announce Type: cross Abstract: An LLM judge scores a bank of responses against a rubric, and the reliability comes back at 0.52. What has been measured? Judge evaluation has begun b
arXiv:2609.29228v1 Announce Type: new Abstract: Finite state machine (FSM) and behavior trees (BT) are widely adopted behavioral modeling paradigms for autonomous intelligent systems. While functional
arXiv:2609.28870v1 Announce Type: cross Abstract: Long-running LLM applications repeatedly send growing context, making prefix caching critical for reducing prefill cost. Yet prefix-cache behavior und
arXiv:2609.29333v1 Announce Type: cross Abstract: One long-form exam in a large course costs hundreds of grader-hours, and qualified graders are scarce; LLM graders are a tempting alternative. To show
arXiv:2609.27955v1 Announce Type: new Abstract: Prediction sets built from an LLM judge can undercover when deployment traffic changes the prevalence of task or policy groups. Weighted conformal predi
arXiv:2609.28026v1 Announce Type: cross Abstract: We investigate whether state-of-the-art large language models (LLMs) generate feedback that reflects the pedagogical practices of expert teachers in t
MLPerf Training v6.1 adds an agentic reinforcement-learning workload that measures how quickly systems can teach a 397-billion-parameter language model to repair real software projects. The post MLPer
arXiv:2609.27954v1 Announce Type: new Abstract: A scalar recalibration map fitted for an LLM judge on one task can fail when the task distribution changes, but the source-target accuracy gap is often
arXiv:2609.25624v1 Announce Type: cross Abstract: Large language model (LLM) outputs are expected to be reproducible under greedy decoding, yet in practice the same model, prompt, and software stack p
arXiv:2609.25047v1 Announce Type: new Abstract: Autonomous agents that automatically build artificial intelligence (AI) models could broaden access to AI across science and engineering. A popular line
arXiv:2609.24662v1 Announce Type: new Abstract: LLM-based agents increasingly operate in environments where they interact with users, tools, and external systems. Yet most security evaluations assume
arXiv:2609.25645v1 Announce Type: cross Abstract: Exhaustively evaluating every candidate LLM configuration on every benchmark item to identify a high-performing one is costly. We formulate configurat
arXiv:2609.25686v1 Announce Type: cross Abstract: Long-horizon assigned work requires an LLM agent to track the state of a task: which steps are done, blocked, cancelled, or open to repetition. Agent
We benchmarked Jev against Claude Opus 5 and GPT-5.6 Terra on accuracy, cost, and latency. Learn how threshold tuning changes hallucination detection. The post Jev vs. LLM-as-a-Judge: Accuracy and cos
arXiv:2609.25051v1 Announce Type: new Abstract: Dual-source encrypted points of interest (DSEP), POIs from two encrypted coordinate systems, suffer from intertwined location and attribute uncertaintie
arXiv:2609.22599v1 Announce Type: new Abstract: Large language model (LLM) judges provide a flexible and scalable method for evaluating model and agent outputs, but their verdicts can be sensitive to
arXiv:2609.26219v1 Announce Type: cross Abstract: Long-running LLM agent workflows often revise interior context spans while retaining long suffixes. Although suffix tokens remain unchanged, altered c
arXiv:2609.26184v1 Announce Type: new Abstract: The integration of Large Language Models (LLMs) into robotic control systems is enabling a new generation of autonomous agents capable of complex reason
arXiv:2609.23889v1 Announce Type: cross Abstract: Automated kernel vulnerability reproduction is essential for bug triage, patch validation, and regression testing, but still lacks an effective and ef
arXiv:2609.25482v1 Announce Type: new Abstract: Large language model (LLM) pretraining conventionally returns the raw final iterate. This couples two design choices: the learning-rate schedule that ge
arXiv:2609.23790v1 Announce Type: new Abstract: Every node in a multi-agent large language model (LLM) workflow retrieves context from memory and injects it into its prompt, where those injected token
arXiv:2509.00961v3 Announce Type: replace-cross Abstract: Active learning is a general learning mechanism shared by artificial and human learners. Whether AI can teach humans such a strategy that tran
arXiv:2609.23490v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly execute multi-step workflows through tool use and interaction with users and environments. However, curre
arXiv:2609.23257v1 Announce Type: cross Abstract: Time series forecasting underpins critical decision-making across diverse domains. While large language models (LLMs) offer promising reasoning capabi
arXiv:2609.22510v1 Announce Type: cross Abstract: As LLM applications integrate with external tools, they are increasingly exposed to indirect prompt injection (IPI), where adversarial instructions ar
arXiv:2609.24967v1 Announce Type: cross Abstract: LLM agents are increasingly deployed in collaborative settings, yet long-term interaction may give rise to undesirable coordination. We study the emer