Knowledge catalogue
arXiv:2609.03254v1 Announce Type: new Abstract: Large Language Models (LLMs) often help users generate artifacts through iterative cycles of generation and revision in conversation. A challenge here i
arXiv:2609.03035v1 Announce Type: cross Abstract: LLM agents are increasingly deployed in multi-agent systems, where they can collude while keeping their actions benign. Output monitors designed to de
arXiv:2604.07119v2 Announce Type: replace Abstract: Peer review plays a central role in the NLP publication process, but is susceptible to various biases. Here, we study language-of-study (LoS) bias:
arXiv:2609.02074v1 Announce Type: new Abstract: Planning is a central capability that enables agents to decompose complex long-horizon tasks into manageable steps. Test-time search and training-based
arXiv:2601.05520v2 Announce Type: replace Abstract: Despite strong performance on many tasks, large language models (LLMs) show limited ability in historical and cultural reasoning, particularly in no
arXiv:2609.02417v1 Announce Type: cross Abstract: Multi-turn agentic RL increasingly treats credit assignment as a targeting problem: given a terminal verifiable reward, per-turn methods localize cred
arXiv:2609.01925v1 Announce Type: cross Abstract: The attention prefilling phase of long-context LLM inference scales quadratically, making self-attention a severe computational bottleneck. Traditiona
arXiv:2609.02275v1 Announce Type: cross Abstract: Large language models are trained to model conditional distributions over text, yet it remains inadequately understood whether they capture the full d
arXiv:2609.02783v1 Announce Type: new Abstract: Evaluating LLM agents is essential for guiding their development, yet it has grown prohibitively expensive: a single pass of a frontier model over an ag
arXiv:2609.02133v1 Announce Type: new Abstract: Empathetic response generation requires models to decide not only what to say, but also how to respond to the previous speaker's affective situation. We
arXiv:2607.09791v2 Announce Type: replace-cross Abstract: The multiplicative repetition penalty shipped across the LLM inference ecosystem (HuggingFace, vLLM, llama.cpp, and a dozen further engines) b
arXiv:2609.02772v1 Announce Type: new Abstract: Low-resource authorship style transfer (LAST) aims to rewrite text into the style of an arbitrary target author using only a few reference examples whil
arXiv:2609.02396v1 Announce Type: new Abstract: Radiology reports are written primarily for clinicians, and their specialized terminology often makes them difficult for patients to interpret. As a res
arXiv:2609.02760v1 Announce Type: new Abstract: On-premise assistants can give factory workers conversational access to machine documentation, but models capable of the task rarely fit shop-floor hard
Discovered that using a realtime llm + h3 world simulation, you can allow multiple different simultaneous character instructions that are restricted to only controlling their respective character. If
This is mostly for setting up for expectation, since personally without LLM i could take 3 days (15 hours of active programming) to debug or implement a feature, but with Qwen 27B (even before Qwen 3.
arXiv:2609.02366v1 Announce Type: cross Abstract: Named Entity Recognition (NER) has achieved substantial progress since the advent of large language models (LLMs). Nevertheless, the recognition of lo
OpenAI Group PBC today started opening access to GPT-6 Astra, its newest and most capable large language model. The company stated that the LLM demonstrates “state of the art” performance in multiple
arXiv:2606.15255v2 Announce Type: replace Abstract: Coordinating heterogeneous multi-robot systems (MRS) for complex, long-horizon tasks requires both flexible high-level reasoning and efficient execu
arXiv:2609.02236v1 Announce Type: new Abstract: Group-based reinforcement learning (RL) has become an effective paradigm for LLM post-training, but in multi-turn agentic tasks with sparse terminal rew
arXiv:2407.14845v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely used in decision-making across diverse domains. Ensuring the generation of safe and reliable responses
arXiv:2609.01693v1 Announce Type: cross Abstract: Safety properties assessed separately for Model Context Protocol (MCP) tool use and Agent2Agent (A2A) delegation need not describe behavior when one a
arXiv:2609.02786v1 Announce Type: new Abstract: The performance of LLM-based agents is jointly shaped by the base model and the harness used when interacting with the environment. This exposes them to
arXiv:2609.02115v1 Announce Type: cross Abstract: Natural language interfaces to databases have traditionally suffered from three structural limitations: exclusive targeting of relational SQL, uncondi
arXiv:2609.02651v1 Announce Type: new Abstract: While English language models have been widely examined for anti-queer bias, Dutch models remain understudied. To address this gap, we developed a cultu
arXiv:2607.18358v2 Announce Type: replace Abstract: Document classification is a solved problem in the laboratory and an unsolved one in the enterprise. The blocker is rarely model architecture; it is
arXiv:2609.00940v1 Announce Type: new Abstract: Solving problems through repeated attempts is a sequential modeling task: at each step, the solver receives feedback and decides how to revise their sol
// Agent Zero Memory // This work separates three things that agent memory systems usually collapse into one. If you build agents with long-term memory, this memory design is a worth a read. Here is h
arXiv:2609.01286v1 Announce Type: new Abstract: Sharing analog integrated circuit designs remains difficult: foundry non-disclosure agreements restrict the process details a design depends on, and the
arXiv:2603.29093v3 Announce Type: replace-cross Abstract: LLM agents rerun full reasoning for every task, even one they solved moments earlier. We introduce extbf{APEX-EM}, a non-parametric experience
arXiv:2609.00274v1 Announce Type: new Abstract: Two-sided service marketplaces are moving from deterministic request-form intake to AI-native probabilistic matching, enabled by large language models (
arXiv:2609.00445v1 Announce Type: cross Abstract: Deployed language model safeguards (safety fine-tuning, filtering, unlearning) vary by principal only outside the model weights: filters are reconfigu
arXiv:2609.01575v1 Announce Type: new Abstract: Extracting structured fields from hundreds of millions of documents annually remains costly in regulated industries: bespoke OCR cascades cover only a f
arXiv:2609.01038v1 Announce Type: new Abstract: A/B testing is the gold standard for evaluating product changes, but each experiment requires real user traffic, engineering effort, and weeks of measur
arXiv:2609.00407v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models enable efficient scaling of large language model (LLM) inference but suffer from substantial data-movement overhead wh
arXiv:2609.00479v1 Announce Type: new Abstract: For emerging scientific research domains, local Small Language Models (SLMs) are becoming more attractive, as they offer stronger privacy control and mo
arXiv:2508.06374v4 Announce Type: replace Abstract: With the surge of large language models (LLMs) and their ability to produce customized output, style-personalized text generation--'write like me'--
arXiv:2609.01526v1 Announce Type: new Abstract: Scientific agents must learn not only how to reason, but also what to believe. However, existing LLM agents typically express scientific hypotheses in f
arXiv:2609.01245v1 Announce Type: cross Abstract: Reinforcement learning is a natural way to post-train LLM agents for long-horizon interactive tasks judged only by end-of-task verification, yet a sha
arXiv:2609.00404v1 Announce Type: cross Abstract: Robot capability marketplaces, the 'app store for robot skills,' are emerging as the deployment vector for LLM-driven robot fleets. The default cloud-
arXiv:2609.01481v1 Announce Type: new Abstract: This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and us
arXiv:2609.01106v1 Announce Type: cross Abstract: When a hint turns a failing generated program into a passing one, does it provide missing information or merely steer the model toward a solution it c
arXiv:2609.00251v1 Announce Type: new Abstract: As people increasingly interact with LLM assistants in daily life, continually adapting to individual preferences has become essential for effective lon
arXiv:2609.01361v1 Announce Type: new Abstract: Linear classifiers trained on hidden states of a large language model (LLM), linear probes, can flag factual errors from a single forward pass. Geometri
arXiv:2511.21638v2 Announce Type: replace Abstract: Practical LLM agents often operate over multi-turn conversations where success is determined only after the full interaction ends. Most multi-turn R
arXiv:2609.01090v1 Announce Type: new Abstract: Scientific knowledge about AI models is produced faster than the community can organize it. Every few months a new foundation model reshapes the field a
arXiv:2609.01408v1 Announce Type: new Abstract: A fundamental challenge in artificial intelligence is the transformation of observations into explicit symbolic representations suitable for abstraction
arXiv:2609.00813v1 Announce Type: new Abstract: While reinforcement learning has enabled LLM-based search agents to invoke external tools, existing methods train under fixed budgets and cannot adapt w
arXiv:2609.01068v1 Announce Type: new Abstract: The heavy-tailed distribution of output lengths in Large Language Model (LLM) serving poses major challenges for resource provisioning and cluster sched
arXiv:2609.01024v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by activating a sparse subset of experts per token. However
arXiv:2609.00275v1 Announce Type: new Abstract: Fleets of LLM agents now externalize effects that cannot be fully undone: they move money, deploy code, delete data, and disclose information. Current c
arXiv:2609.00969v1 Announce Type: cross Abstract: We present the zbMATH Open Knowledge Graph, a large-scale RDF knowledge graph (KG) covering more than 250 years of mathematical scholarship. Unlike ex
arXiv:2609.00296v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly proposed for healthcare tasks such as clinical documentation, evidence retrieval, patient messaging,
arXiv:2609.00057v1 Announce Type: cross Abstract: Value signals are aggregated user-level moral representations that capture users' inferred value-related tendencies from their online discourse. User
arXiv:2609.00920v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) requires an agent to navigate through unseen 3D environments according to natural-language instructions. Explicit
arXiv:2608.28592v1 Announce Type: new Abstract: Large language models (LLMs) achieve high scores on medical knowledge examinations, yet real-world oncology is not a knowledge test--it is a sequence of
arXiv:2601.12449v2 Announce Type: replace-cross Abstract: AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper to
arXiv:2602.02475v2 Announce Type: replace Abstract: AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy t
arXiv:2310.04363v3 Announce Type: replace-cross Abstract: Autoregressive large language models (LLMs) compress knowledge from their training data through next-token conditional distributions. This lim
arXiv:2608.29529v1 Announce Type: cross Abstract: Semantic alignment between specialized normative texts is challenging when equivalent requirements use different terms, syntax, and levels of abstract