Knowledge catalogue
arXiv:2603.01092v2 Announce Type: replace Abstract: Scientific discovery is constrained not only by what is true, but by what is cognitively available to the researchers currently exploring a field. M
arXiv:2605.16787v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Reward (RLVR) has proven effective in improving Large Language Model's (LLM) reasoning ability. However, the le
arXiv:2605.17821v1 Announce Type: cross Abstract: Large Language Model (LLM) training is frequently interrupted by a heterogeneous spectrum of failures, from common GPU crashes to catastrophic cluster
arXiv:2605.17170v1 Announce Type: new Abstract: Agentic workloads have emerged as a major workload for LLM inference. They differ significantly from chat-only workloads, requiring long-context process
arXiv:2601.17887v2 Announce Type: replace Abstract: Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized ag
arXiv:2605.15871v1 Announce Type: new Abstract: Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers. We introduce a dual-
arXiv:2605.15206v1 Announce Type: cross Abstract: Autonomous agents powered by large language models (LLMs) are increasingly used to automate complex, multi-step tasks such as coding or web-based ques
B9208 is a build release of llama.cpp, an open-source C/C++ project that enables efficient large language model inference on diverse hardware platforms. The llama.cpp project focuses on optimized LLM
b9221 is an intermediate build release from the llama.cpp project, which is a C/C++ implementation enabling efficient LLM inference on consumer hardware. The release includes platform-specific binarie
arXiv:2601.21702v3 Announce Type: replace-cross Abstract: We consider Representation Misdirection (RM), a class of large language model (LLM) unlearning methods that achieve forgetting by redirecting
arXiv:2605.15315v1 Announce Type: new Abstract: LLM-powered coding agents spend the majority of their token budget reading repository files, yet much of the retrieved code is irrelevant to the task at
arXiv:2602.00747v2 Announce Type: replace-cross Abstract: Determining an effective data mixture is a key factor in Large Language Model (LLM) pre-training, where models must balance general competence
arXiv:2605.15701v1 Announce Type: cross Abstract: Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'
arXiv:2512.04111v2 Announce Type: replace-cross Abstract: LLM-powered coding agents are reshaping the development paradigm. However, existing evaluation systems, neither traditional tests for humans n
arXiv:2605.16023v1 Announce Type: new Abstract: LLM-as-a-judge has become the dominant paradigm for grading model outputs at scale, yet the same model assigns systematically different scores when its
arXiv:2605.15572v1 Announce Type: new Abstract: The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characte
arXiv:2605.15436v1 Announce Type: new Abstract: This paper presents a comprehensive analysis of neural activation patterns across six distinct large language model (LLM) architectures, examining their
arXiv:2605.15215v1 Announce Type: new Abstract: Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are t
arXiv:2605.15581v1 Announce Type: new Abstract: LLM-based root cause analysis (RCA) agents have recently emerged as a promising paradigm for incident diagnosis in microservice AIOps. However, their re
arXiv:2605.13850v1 Announce Type: new Abstract: Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus o
arXiv:2605.14271v1 Announce Type: new Abstract: LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. Howev
b9159 is a release of llama.cpp published on May 14, 2026 . llama.cpp is a C/C++ implementation of large language model inference that enables efficient LLM execution on consumer hardware with minimal
arXiv:2605.14362v1 Announce Type: cross Abstract: Context window efficiency is a practical constraint in large language model (LLM)-based developer tools. Paulsen [12] shows that all tested models deg
arXiv:2605.14465v1 Announce Type: new Abstract: Multi-step LLM reasoning over structured tables fails because planning and execution share no explicit cell-grounding contract. Existing methods constra
arXiv:2605.13848v1 Announce Type: new Abstract: Agentic LLM frameworks that rely on prompted orchestration, where the model itself determines workflow transitions, often suffer from hallucinated routi
ICYMI: 1️⃣ LangSmith Engine 2️⃣ SmithDB 3️⃣ Managed Deep Agents 4️⃣ LangSmith Sandboxes: Now Generally Available 5️⃣ Context Hub 6️⃣ LangSmith LLM Gateway 7️⃣ Sandboxes, Prebuilt agents, + free model
arXiv:2605.15102v1 Announce Type: cross Abstract: Large language model (LLM) based multi-turn dialogue systems often struggle to track dependencies across non-adjacent turns, undermining both consiste
Inference is becoming the largest compute market and energy consumer in AI. Pearl turns inference CapEx of hyperscalers into a profit center: every LLM token produced by GPUs can simultaneously genera
arXiv:2605.15184v1 Announce Type: new Abstract: Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools,
arXiv:2605.15156v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Ma
arXiv:2605.14978v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by having a lightweight draft model propose speculative windows of candidate tokens for parallel verifica
arXiv:2605.15155v1 Announce Type: cross Abstract: Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coars
arXiv:2605.14866v1 Announce Type: cross Abstract: As modern microservice systems grow increasingly complex due to dynamic interactions and evolving runtime environments, they experience failures with
The search did not return specific information about the b9140 release. Based on the context, b9140 is a specific build number from the llama.cpp project releases. llama.cpp is an LLM inference implem
arXiv:2605.12520v1 Announce Type: cross Abstract: Taxonomy induction is crucial for organizing concepts into explicit and interpretable semantic hierarchies. While existing methods have achieved promi
arXiv:2605.13295v1 Announce Type: cross Abstract: LLM-based multi-agent systems have demonstrated strong performance across complex real-world tasks, such as software engineering, predictive modeling,
arXiv:2605.12718v1 Announce Type: new Abstract: Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain structu
arXiv:2509.18993v3 Announce Type: replace Abstract: Low-rank architectures have become increasingly important for efficient large language model (LLM) pre-training, providing substantial reductions in
arXiv:2605.13740v1 Announce Type: new Abstract: Whether navigating a building, operating a robot, or playing a game, an agent that acts effectively in an environment must first learn an internal model
arXiv:2605.13037v1 Announce Type: new Abstract: Current interactive LLM agents rely on goal-conditioned stepwise planning, where environmental understanding is acquired reactively during execution rat
arXiv:2605.12838v1 Announce Type: new Abstract: Tracking an interpretable emotional arc of a conversation via the sentiment of individual utterances processed as a whole is central to both understandi
arXiv:2605.12991v1 Announce Type: cross Abstract: LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagreement at rates we term yield, a vulnerability widel
arXiv:2605.13501v1 Announce Type: cross Abstract: LLM-based generation of SystemVerilog Assertions (SVA) is often reported as nearing saturation, with the strongest specialized model reaching {sim}76%
so cool. win for the shape rotators! @ericho_goodfire Neural networks do math by rotating shapes. We found a shape-rotating calculator hidden inside an LLM – and it’s used for more than just math! (1/
arXiv:2605.12947v1 Announce Type: cross Abstract: LLM-enabled AI workflows increasingly produce outputs through iterative generate-evaluate-revise loops. Each iteration can improve the candidate, but
5/5 Ensemble: Run multiple distinct agent configs in parallel → select the best trajectory. Leverages success of the portfolio vs single variants (see also: @/karpathy’s LLM Council). Can outperform b
arXiv:2605.12197v1 Announce Type: new Abstract: Leveraging Graph Neural Networks (GNNs) as graph encoders and aligning the resulting representations with Large Language Models (LLMs) through alignment
Amazon is bringing Alexa Plus to Amazon.com, integrating its LLM-powered AI assistant directly into the company's shopping experience. Beginning today, when you type a query into Amazon, you'll be tal
b9129 is a build release of llama.cpp, a C/C++ implementation for LLM inference . As part of the llama.cpp project's release cycle, this build represents an intermediate development version containing
arXiv:2605.11221v1 Announce Type: cross Abstract: Predictive models in biomedicine depend on structured assay data locked in the text, tables, and supplements of primary publications. This bottleneck
arXiv:2605.12177v1 Announce Type: new Abstract: [Abridged] Production LLM deployments receive feedback from a non-random fraction of users: thumbs sit mostly in the tails of the satisfaction distribut
arXiv:2602.09725v3 Announce Type: replace-cross Abstract: Remote KV cache reuse fetches KV cache for identical contexts from remote storage, avoiding recomputation, accelerating LLM inference. While i
arXiv:2605.11403v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, with Group Relative Policy Opti
arXiv:2605.11051v1 Announce Type: cross Abstract: LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promis
arXiv:2605.12419v1 Announce Type: new Abstract: Despite the rapid advancements in large language model (LLM) development, fine-tuning them for specific tasks often results in the catastrophic forgetti
arXiv:2605.11608v1 Announce Type: new Abstract: Comparing post-training LLM variants, such as quantized, LoRA-adapted, and distilled models, requires a diagnostic that identifies how a variant has dri
arXiv:2605.12260v1 Announce Type: new Abstract: Long-horizon language agents accumulate conversation history far faster than any fixed context window can hold, making memory management critical to bot
arXiv:2605.11290v1 Announce Type: new Abstract: Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller on
arXiv:2605.12264v1 Announce Type: cross Abstract: Supervised Finetuning (SFT) has become one of the primary methods for adapting a large language model (LLM) with extensive pre-trained knowledge to do
arXiv:2605.10999v1 Announce Type: new Abstract: Skills are a promising way to improve LLM agent capabilities without retraining, while keeping the added procedure reusable and controllable. However, h