Knowledge catalogue
arXiv:2507.15903v2 Announce Type: replace-cross Abstract: Empowered by large language models (LLMs), intelligent agents have become a popular paradigm for interacting with open environments to facilit
This release candidate introduces support for offloading the image GPU projection (mmproj) to an integrated GPU when using fit padding in Ollama's LLM processing, addressing technical improvements for
Nonuniform Tensor Parallelism (NTP) enables large-scale LLM training jobs to dynamically adapt tensor parallelism degree in response to transient GPU unavailability, ensuring sustained Goodput and min
Fable 5 is an absolute beast at threejs. It's the best LLM at generating 3D simulations/worlds. Watch how I combine it with gpt-realtime-2 to generate interactive educational 3D worlds @dair_ai. Comme
The Log is the Agent 它的核心观点是：不要把日志当成 agent 的副产品，而要把 append-only event log 当成 agent 本身。 在 ActiveGraph 里，目标、规则、工具调用、LLM 响应、产物和关系都写入同一条事件日志；当前状态只是日志 replay 后投影出来的一张图。 这样带来三个关键能力： 可确定性重放 可在任意事件处分叉实验 从最终输出
Here's a cool piece of LLM lore: the original scaling laws were wrong due to a bug, which probably led to a lot of wasted compute on oversized undertrained models 🫣 (and that was before we even starte
arXiv:2607.01867v1 Announce Type: cross Abstract: The use of LLMs in software development has become increasingly widespread on tasks such as code generation and summarization. Reports from large tech
arXiv:2607.02329v1 Announce Type: new Abstract: Autonomous-research agents have demonstrated end-to-end LLM automation in machine-learning sandboxes where execution provides calibration. Frontier phys
arXiv:2607.01740v1 Announce Type: new Abstract: Public LLM leaderboards optimise for global average performance and do not capture the specific cognitive demands of financial-services work: a model th
arXiv:2604.02091v2 Announce Type: replace-cross Abstract: Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation. However, current reranking models are typicall
arXiv:2607.01595v1 Announce Type: new Abstract: As the scale and complexity of cloud-based AI systems continue to escalate, ensuring service reliability through rapid fault detection and adaptive reco
arXiv:2607.01793v1 Announce Type: new Abstract: LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testin
arXiv:2607.02049v1 Announce Type: cross Abstract: Large Language Models are increasingly deployed in emotional-support contexts and crisis-related situations. Nevertheless, their cross-lingual abiliti
arXiv:2607.02043v1 Announce Type: cross Abstract: Disaggregated LLM serving runs prefill and decode on separate GPU pools to keep the two phases from interfering. In practice, this creates a new asymm
arXiv:2607.02507v1 Announce Type: new Abstract: LLM agents will increasingly act in socially structured settings where role, audience, and relational context can shape what is advantageous or costly t
arXiv:2607.00297v1 Announce Type: cross Abstract: When LLM agents use evaluator feedback to adapt their behavior in closed loops, evaluator biases propagate through the agent's strategy distribution -
I've been blogging a few of my Fable experiments today, most recently I had it more-or-less one-shot a CLI coding agent on top of my LLM Python library https://simonwillison.net/2026/Jul/2/llm-coding-
arXiv:2607.01233v1 Announce Type: cross Abstract: LLMs are increasingly used to brainstorm research ideas, but existing evaluations mostly judge individual ideas by novelty, feasibility, or expert pre
arXiv:2607.00760v1 Announce Type: new Abstract: Long-context LLM services now sustain prompts with hundreds of thousands to millions of tokens, making the key-value (KV) cache a first-order serving co
arXiv:2607.00006v1 Announce Type: cross Abstract: Beckmann & Butlin's (2026) ontological framework for the LLM individuation problem inherits an unargued cross-regime co-reference assumption from the
arXiv:2607.00692v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate tool results, files, plans, and user constraints that are too structured to be treated as a disposable text suffix. C
arXiv:2607.00011v1 Announce Type: cross Abstract: Reusable skill libraries are becoming important infrastructure for large language model (LLM) agents, yet existing selection methods often treat skill
arXiv:2606.30877v1 Announce Type: cross Abstract: Recent literature shows that large language models (LLMs) are useful for general-purpose tasks yet perform poorly on specific domain ones. One reason
arXiv:2606.31635v1 Announce Type: cross Abstract: Fault recovery in process plants still relies heavily on plant operators, especially when faults fall outside predefined supervisory logic. Operators
arXiv:2606.31309v1 Announce Type: cross Abstract: While post-training backdoor detection and trigger inversion schemes have been developed for AIs used e.g. for images, there is a paucity of such meth
arXiv:2508.10409v3 Announce Type: replace-cross Abstract: This paper constructs a textual dataset for training large language models (LLMs) to learn analog circuit knowledge and customizes LLM trainin
arXiv:2606.30668v1 Announce Type: cross Abstract: What happens when LLM agents operate with no context outside a turn, minimal prompting, and simple tools? Inspired by swarm engineering, we give colle
arXiv:2510.10895v2 Announce Type: replace Abstract: Medium Access Control (MAC) protocols, essential for wireless networks, are typically manually configured. While deep reinforcement learning (DRL)-b
arXiv:2606.31046v1 Announce Type: new Abstract: Artificial life has explored life-like behavior on many computational substrates, but mostly in researcher-designed closed worlds. We argue that large l
arXiv:2606.32034v1 Announce Type: cross Abstract: LLM agents increasingly act over long horizons, where a single trajectory can contain hundreds or thousands of actions. In these settings, outcome-onl
arXiv:2606.31121v1 Announce Type: new Abstract: Sequentially evolving LLM memory enables agents to reuse past experience, but existing systems usually deploy each locally generated memory update witho
arXiv:2606.29719v1 Announce Type: cross Abstract: Measurements of proprietary LLM evaluators can become invalid within weeks -- we document one case and provide the diagnostic framework to detect it.
arXiv:2606.29193v1 Announce Type: cross Abstract: LLM-based agents are reshaping microservice operations into AgentOps, where benchmarks are key to evaluating failure diagnosis over multimodal observa
arXiv:2606.28467v1 Announce Type: cross Abstract: Appliance-level energy monitoring in office buildings produces noisy alerts that non-expert facility managers struggle to use. This paper proposes an
arXiv:2606.29920v1 Announce Type: new Abstract: Rubric-based scoring has become a widely used paradigm in model evaluation, typically with LLM-as-a-Judge (LaaJ) for rubric scoring. However, the reliab
arXiv:2606.28679v1 Announce Type: cross Abstract: Tool-using LLM agents increasingly read untrusted content while holding side-effecting tools such as payments, email, CRM, and infrastructure APIs, ye
arXiv:2511.02734v3 Announce Type: replace Abstract: Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability
arXiv:2606.29947v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as rerankers in recommender systems, with the expectation that semantic understanding will help in
arXiv:2606.29929v1 Announce Type: new Abstract: Distilling historical trajectories into reusable experience to enhance future problem-solving has become a focal point of recent LLM research. However,
In this post, you will learn five practical patterns for building resilient generative AI applications on AWS, progressing from native Amazon Bedrock features to multi-model orchestration using an LLM
arXiv:2606.29900v1 Announce Type: cross Abstract: Personality recognition in asynchronous video interviews (AVIs) has become increasingly important due to their widespread adoption in modern recruitme
arXiv:2508.06133v4 Announce Type: replace-cross Abstract: We study offline scheduling for large language model (LLM) serving under a fixed KV-cache memory budget, where requests have heterogeneous pro
arXiv:2606.16364v2 Announce Type: replace Abstract: LLM agents mis-call tools, and the natural guess is that the model failed to see the right tool in a crowded harness. We show the opposite through a
arXiv:2606.30317v1 Announce Type: cross Abstract: The Model Context Protocol (MCP), introduced by Anthropic in November 2024, defines a standardized interface for connecting large language models (LLM
arXiv:2606.30634v1 Announce Type: new Abstract: Modern large-scale LLM pretraining benefits from utilizing Pipeline Parallelism; however, synchronous implementations leave GPUs idle during pipeline bu
arXiv:2606.29225v1 Announce Type: new Abstract: LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts. Prior
arXiv:2606.30389v1 Announce Type: new Abstract: Dynamic sparse attention (DSA) accelerates long-context LLM decoding by attending to only the top-K KV blocks relevant to each query, but it introduces
arXiv:2606.28798v1 Announce Type: new Abstract: Objective: ICD codes are central to reimbursement, research, and population health surveillance, yet automated coding systems often struggle to integrat
arXiv:2606.29296v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) is a default recipe for process-supervised reinforcement learning of LLM reasoners, and dense process supervis
arXiv:2606.28589v1 Announce Type: new Abstract: Current approaches to enhance Large Language Model (LLM) reasoning, such as Chain-of-Thought and 'Wait' prompts, primarily encourage models to think mor
arXiv:2606.30639v1 Announce Type: new Abstract: World models offer a principled way to equip long-horizon LLM agents with foresight: predictions of action consequences before execution. However, unrel
arXiv:2606.28839v1 Announce Type: new Abstract: We introduce the Contagion Tensor, a measurement framework for quantifying how large language model (LLM) output distributions couple across modalities,
arXiv:2606.29581v1 Announce Type: cross Abstract: Modern LLM deployments routinely compress models and raise sampling temperature to reduce cost, latency, or repetition, yet safety evaluations usually
The most important weird thing about LLMs is that they are so general. A bigger LLM that is better at coding is also better at ideation & ethical advice & medicine & math. This isn’t true of everythin
arXiv:2606.29067v1 Announce Type: new Abstract: We present ThinkProbe, a framework for structural analysis of LLM reasoning traces. ThinkProbe converts each trace into a Thought Graph a directed graph
arXiv:2606.30445v1 Announce Type: new Abstract: Online imitation learning (IL), particularly on-policy distillation, has emerged as a strong LLM post-training approach, often outperforming offline sup
arXiv:2606.30383v1 Announce Type: new Abstract: A rapidly growing class of LLM agents is multi-party: the agent acts for a principal (who briefs it, sends follow-ups, and receives results) while also
arXiv:2606.28186v1 Announce Type: cross Abstract: Predicting human item difficulty is central to educational assessment, where reliable estimates support fairness and effective test construction. Exis
arXiv:2606.27611v1 Announce Type: new Abstract: Operations Research (OR) provides a rigorous framework for high-stakes decision-making, but effective OR modeling requires substantial domain knowledge,
arXiv:2606.27409v1 Announce Type: cross Abstract: Multi-agent large language model (LLM) systems often rely on verifier and critic agents to suppress hallucinations, but verification is delayed. Durin