Knowledge catalogue
arXiv:2503.18760v2 Announce Type: replace Abstract: A key consideration when training an LLM is whether the target language is more or less resourced, for example English compared to Welsh, or Python
arXiv:2602.22586v2 Announce Type: replace-cross Abstract: Synthetic tabular data generation has attracted growing attention due to its importance for data augmentation, foundation models, and privacy.
arXiv:2605.10991v1 Announce Type: new Abstract: Existing approaches to LLM personalization focus on constructing better personalized models or inputs, while treating inference as a single-shot process
We just shipped tons of new products to accelerate the full agent development lifecycle: https://www.langchain.com/blog TLDR: ✅ LangSmith Engine ✅ SmithDB ✅ Sandboxes ✅ Managed Deep Agents ✅ LLM Gatew
arXiv:2410.13181v2 Announce Type: replace Abstract: Recent advancements in large language models (LLMs) have been remarkable. Users face a choice between using cloud-based LLMs for generation quality
arXiv:2605.09992v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by drafting future tokens with a small model, but drafter models degrade sharply under template perturb
b9123 is a release of llama.cpp created on May 12, 2026 . llama.cpp is an open source software library that performs inference on various large language models such as Llama , providing LLM inference
arXiv:2605.10195v1 Announce Type: new Abstract: Tree-of-Thought (ToT) reasoning structures Large Language Model (LLM) inference as a tree-based search, demonstrating strong potential for solving compl
arXiv:2605.10598v1 Announce Type: new Abstract: Large language models (LLMs) have emerged as powerful tools for automatic algorithm design (AAD). However, existing pipelines remain inefficient. They o
arXiv:2605.08439v1 Announce Type: new Abstract: Accurately communicating the side effects of cancer treatments to cancer survivors is critical, particularly in settings such as informed consent, where
arXiv:2604.01151v2 Announce Type: replace Abstract: As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human o
arXiv:2603.08065v2 Announce Type: replace-cross Abstract: Structured pruning reduces LLM inference cost by removing low-importance architectural components. This can be viewed as learning a multiplica
arXiv:2605.09331v1 Announce Type: new Abstract: Modern Large Language Model (LLM) training is fundamentally bottlenecked by pathologically flat saddle points in extreme high-dimensional landscapes. Mo
arXiv:2605.08477v1 Announce Type: new Abstract: Explicit planning is a critical capability for LLM-based agents solving complex data-centric tasks, which require precise tool calling over external dat
arXiv:2605.08769v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems have shown strong potential on complex tasks through agent specialization, tool use, and collaborat
arXiv:2605.09923v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become the standard paradigm for LLM mathematical reasoning, where Group Relative Policy Optim
arXiv:2605.08314v1 Announce Type: cross Abstract: SVD-based Low-rank compression reduces transformer parameters and nominal FLOPs, but these savings often translate poorly into real LLM serving speedu
arXiv:2605.08817v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) recently thrives in large language model (LLM) reasoning tasks. However, the reward sparsity and t
arXiv:2605.10407v1 Announce Type: new Abstract: Modern LLM APIs often reveal only top-K logit scores and censor the remaining vocabulary. We study the per-position distribution-recovery limits of this
arXiv:2601.03511v2 Announce Type: replace-cross Abstract: A major challenge for the operation of large language models (LLMs) is how to predict whether a specific LLM will produce sufficiently high-qu
arXiv:2605.08626v1 Announce Type: cross Abstract: Large language models (LLMs) are transforming society, powering applications from smartphone assistants to autonomous driving. Yet cloud-based LLM ser
arXiv:2605.09494v1 Announce Type: cross Abstract: Unmanned underwater vehicles (UUVs) operate persistently in communication-constrained environments, thus requiring high-level autonomous fault-toleran
arXiv:2510.08592v3 Announce Type: replace-cross Abstract: Test-Time Scaling (TTS) improves LLM reasoning by exploring multiple candidate responses and then operating over this set to find the best out
arXiv:2605.08889v1 Announce Type: cross Abstract: Machine learning research has grown exponentially while its communication norms have not. We argue NeurIPS should adopt explicit, measurable writing s
arXiv:2605.09530v1 Announce Type: cross Abstract: As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and u
arXiv:2605.08374v1 Announce Type: new Abstract: Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval
arXiv:2605.08670v1 Announce Type: new Abstract: Large language model (LLM) powered AI agents have emerged as a promising paradigm for autonomous problem-solving, yet they continue to struggle with com
arXiv:2605.10813v1 Announce Type: new Abstract: LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper writing, but a fundamental question remains: automati
arXiv:2601.21619v2 Announce Type: replace-cross Abstract: Parallel thinking improves LLM reasoning through multi-path sampling and aggregation. In standard evaluations, due to a lack of sample-specifi
arXiv:2602.23161v2 Announce Type: replace Abstract: Time series reasoning demands both the perception of complex dynamics and logical depth. However, existing LLM-based approaches exhibit two limitati
arXiv:2605.09287v1 Announce Type: new Abstract: Large Language Model (LLM)-based search agents trained with reinforcement learning (RL) have significantly improved the performance of knowledge-intensi
arXiv:2605.09504v1 Announce Type: cross Abstract: We present swarm-attack, an open-source adversarial testing framework in which multiple lightweight LLM agents coordinate through shared memory, paral
arXiv:2605.09931v1 Announce Type: cross Abstract: Tool-integrated reasoning (TIR) enables large language models (LLMs) to enhance their capabilities by interacting with external tools, such as code in
arXiv:2605.08625v1 Announce Type: cross Abstract: Time Series Foundation Models (TSFMs) excel at numerical forecasting but operate as black boxes lacking qualitative reasoning. Conversely, applying LL
arXiv:2511.00371v2 Announce Type: replace Abstract: In Socratic debugging, instructors guide students towards identifying and fixing a bug on their own, instead of providing the bug fix directly. Most
arXiv:2605.09033v1 Announce Type: cross Abstract: Graph-based agent memory is increasingly used in LLM agents to support structured long-term recall and multi-hop reasoning, but it also creates a new
arXiv:2605.08526v1 Announce Type: new Abstract: While LLM-based agents excel at planning and executing long action sequences, their execution often remains inconsistent across trials, limiting reliabi
arXiv:2605.09359v1 Announce Type: cross Abstract: Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skill
arXiv:2605.10114v1 Announce Type: new Abstract: Large Language Model (LLM)-based agents (e.g., OpenClaw) increasingly rely on reusable skill libraries to solve artifact-rich tasks such as document-cen
arXiv:2605.05443v2 Announce Type: replace-cross Abstract: LLM watermarks must be detectable without compromising text quality, yet most existing schemes bias the next-token distribution and pay for de
arXiv:2605.09329v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by using a fast draft model to generate tokens and a more accurate target model to verify them. Its perfo
arXiv:2605.10754v1 Announce Type: new Abstract: LLM-based foundation agents that perceive, reason, and act across thousands of reasoning steps are rapidly becoming the dominant paradigm for deploying
arXiv:2605.10698v1 Announce Type: cross Abstract: Multi-agent systems (MAS) assume that collaborating inherently improves Large Language Model (LLM) reasoning. We challenge this by demonstrating that
arXiv:2502.01237v3 Announce Type: replace Abstract: Direct Alignment Algorithms (DAAs) simplify LLM alignment by directly optimizing policies, bypassing reward modeling and RL. While DAAs differ in th
arXiv:2605.08737v1 Announce Type: cross Abstract: On-policy distillation (OPD) is widely used for LLM post-training. When pushed with a reward-extrapolation coefficient lambda > 1, the student can lif
arXiv:2605.08234v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by the memory and bandwidth cost of reading large KV caches during decoding. KV compression reduces this co
arXiv:2605.10176v1 Announce Type: cross Abstract: Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models (LLMs) that ena
Ah yes, chatGPT, tell me more about the 'colony mind', 'foraging patrol' and 'nost building' behaviors of the human liver. For anyone predicting near-term physician replacement by LLM-based AI, please
arXiv:2605.07046v1 Announce Type: cross Abstract: Evaluation of large language models (LLMs) is increasingly critical, yet standard benchmarking methods rely on average accuracy, overlooking both the
arXiv:2605.05583v2 Announce Type: replace Abstract: LLM agents that operate over long context depend on external memory to accumulate knowledge over time. However, existing methods typically store eac
arXiv:2605.06702v1 Announce Type: new Abstract: Large language models (LLMs) have become a central foundation of modern artificial intelligence, yet their lifecycle remains constrained by a rigid sepa
arXiv:2605.07488v1 Announce Type: new Abstract: The scaling of Large Multimodal Models (LMMs) is constrained by the quality-quantity trade-off inherent in synthetic data. Previous approaches, such as
arXiv:2605.07244v1 Announce Type: cross Abstract: We introduce Mutual Reinforcement Learning, a framework for concurrent RL post-training in which heterogeneous LLM policies exchange typed experience
arXiv:2605.07692v1 Announce Type: new Abstract: Large-scale social simulators are essential for studying complex social patterns. Prior work explores hybrid methods to scale up simulations, combining
arXiv:2605.07316v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards improves LLM reasoning but often induces overthinking, where models generate unnecessarily long reasoning
arXiv:2605.06832v1 Announce Type: cross Abstract: Accurately understanding the intent behind speech, conversation, and writing is crucial to the development of helpful Large Language Model (LLM) assis
arXiv:2605.07721v1 Announce Type: cross Abstract: Recurrent LLM architectures have emerged as a promising approach for improving reasoning, as they enable multi-step computation in the embedding space
arXiv:2605.07269v1 Announce Type: new Abstract: Indirect prompt injection remains a persistent weakness in retrieval-augmented and tool-using LLM systems, and the problem becomes harder to characteris
Our internal AI agent was a brute-force nightmare. 🛑 It burned 40,000 tokens, took 2 minutes, and only hit 68% accuracy just to answer a single question. Why? Traditional databases are built for human
arXiv:2502.01941v3 Announce Type: replace-cross Abstract: While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on sparse retrie