Knowledge catalogue
arXiv:2609.38860v1 Announce Type: cross Abstract: Learning from human preferences is central to large language model (LLM) alignment, but human preference annotation is costly. Active preference learn
arXiv:2609.38600v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used in clinical settings, it is critical to evaluate their reliability under realistic variation in cl
arXiv:2609.38521v1 Announce Type: cross Abstract: We introduce ShamAN-Q, a sub-1-bit post-training quantization method that extends NanoQuant by replacing each its diagonal reconstruction geometry wit
arXiv:2609.39989v1 Announce Type: new Abstract: Background. A component replacement in a language-model agent changes an execution trajectory, potentially altering later observations, resource use, an
arXiv:2609.36931v1 Announce Type: new Abstract: Reproducibility is essential for scientific research, yet prior work shows that LLM outputs vary with hardware and batching. We identify an overlooked f
arXiv:2609.36187v1 Announce Type: new Abstract: Symbolic Regression (SR) is a data-driven method for scientific discovery which searches for interpretable analytical relationships within data. Recentl
arXiv:2609.37145v1 Announce Type: new Abstract: LLM-as-a-Judge is increasingly used to evaluate policy responses on open-ended tasks that lack ground-truth answers. Existing work often directly conver
arXiv:2609.31857v2 Announce Type: replace Abstract: Validating an LLM-as-a-judge requires estimating its agreement with humans, yet annotation budgets rarely allow every item to be multiply labeled. W
arXiv:2609.36580v1 Announce Type: new Abstract: LLM agents deployed in real-world environments continually encounter new tasks and safety risks, while execution feedback typically becomes available on
arXiv:2609.37294v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for software engineering tasks, yet their stochastic behavior challenges the validity, reproducibil
arXiv:2609.37902v1 Announce Type: new Abstract: Existing LLM routers choose among models using static per-model costs. We show that open-weight inference markets introduce a second, largely ignored de
arXiv:2609.32248v1 Announce Type: new Abstract: Large language model (LLM) leaderboards compare model capabilities by ranking models according to their mean performance on fixed benchmarks. However, v
arXiv:2609.33065v1 Announce Type: cross Abstract: Large language model (LLM) assistants can now search the web and consult external sources while completing user requests. These sources can provide us
arXiv:2609.33016v1 Announce Type: new Abstract: Large Language Model (LLM) pretraining performance is jointly shaped by three components of the training triplet: the optimizer, model architecture, and
arXiv:2609.35760v1 Announce Type: new Abstract: When a large language model (LLM) agent executes the same task, token consumption can vary by over an order of magnitude across runs. The agent chooses
arXiv:2609.31054v1 Announce Type: new Abstract: Large Language Model (LLM) pollution occurs when synthetic responses contaminate data intended to capture human behavior. High deployment costs have so
arXiv:2609.30940v1 Announce Type: new Abstract: Individually protective decisions can produce avoidable collective failures. As large language model (LLM) agents take on greater roles in financial dec
arXiv:2609.30734v1 Announce Type: new Abstract: Multi-agent LLM workflows use planning, execution, verification, and summarization to improve task performance, yet the value of each component depends
arXiv:2609.30967v1 Announce Type: new Abstract: Most work on improving large language models treats accuracy as the sole objective. We argue that the harness, the Python code surrounding the model tha
arXiv:2609.29349v1 Announce Type: cross Abstract: ArGuard is a shared task on harmful content detection in Arabic memes and LLM prompts. It includes two tracks: Track A focuses on multimodal hate dete
arXiv:2609.29508v1 Announce Type: new Abstract: Large language model (LLM) agents may perform well on isolated tasks yet drift into inconsistency over extended interaction. We evaluate temporal consis
Remember October 2022 when you doused Galactica with vitriol? Galactica was a 120b-parameter LLM-based system from Meta-FAIR designed to help scientist write papers. It was open sourced (link below).
arXiv:2602.05145v2 Announce Type: replace-cross Abstract: Speculative decoding can substantially accelerate LLM inference, but realizing its benefits in practice is challenging due to evolving workloa
arXiv:2609.28572v1 Announce Type: cross Abstract: Multi-stage LLM-based cyber agents may complete attack workflows while remaining brittle, costly, or reliant on incorrect interpretations of execution
arXiv:2609.27857v1 Announce Type: cross Abstract: Large language model (LLM) agents often process external tool responses as they arrive, making response timing part of the decision process. We introd
arXiv:2609.26913v1 Announce Type: cross Abstract: No single Large Language Model (LLM) is uniformly reliable across queries, motivating multi-model inference systems that either route among models or
arXiv:2609.28177v1 Announce Type: cross Abstract: LLM leaderboard gains can reflect selection among privately evaluated model variants, yet neither the number of variants nor their dependence is publi
arXiv:2402.17937v2 Announce Type: replace Abstract: Mental health is a significant healthcare challenge, and cognitive behavioral therapy (CBT) is a widely used therapeutic method for treating anxiety
arXiv:2609.27349v1 Announce Type: new Abstract: Real-world molecular design remains challenging for large language model (LLM)-based agents. It requires them to interpret design contexts, satisfy mult
arXiv:2609.27296v1 Announce Type: cross Abstract: Validating Autonomous Driving Systems (ADS) in simulation requires testing architectures that can discover rare, safety-critical failures while genera
arXiv:2609.25537v1 Announce Type: new Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing latenc
arXiv:2509.20702v3 Announce Type: replace-cross Abstract: Recent advances in large language model (LLM) embeddings have enabled powerful representations for biological data, but most applications to d
Interesting paper on agent memory stored as a linked markdown wiki. Lots of great ideas and insights if you work with LLM Wikis. Wikis are useful for agents because each page holds dense text and the
arXiv:2509.20634v3 Announce Type: replace-cross Abstract: We provide a new framework for estimating peer effects when outcomes are multivariate behavioral measures derived from written text using an L
arXiv:2609.23097v1 Announce Type: cross Abstract: Internet of Things (IoT) systems are increasingly deployed in smart homes, transportation, energy systems, and critical infrastructure. This broad con
arXiv:2609.23039v1 Announce Type: new Abstract: LLM-based AI systems answer political questions for hundreds of millions of people. Current audits measure what they say to an average user, but their b
arXiv:2609.22971v1 Announce Type: new Abstract: Evaluating user experience (UX) on live websites through user testing is expensive, subjective, and difficult to scale. LLM agents offer a promising rou
arXiv:2609.22252v1 Announce Type: new Abstract: We present CALM, a reproducible hybrid framework that integrates an optional large language model (LLM) activity planner with calibrated stochastic choi
arXiv:2604.06487v2 Announce Type: replace Abstract: Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR archi
arXiv:2609.22553v1 Announce Type: new Abstract: Effective LLM tutoring depends on correctly identifying the specific error in a student's reasoning before generating feedback. We study this problem in
arXiv:2609.22196v1 Announce Type: cross Abstract: We present EvoRank, an open autonomous ranking engineer: an LLM-guided evolutionary loop that discovers complete Learning-to-Rank pipelines (features,
arXiv:2609.22880v1 Announce Type: cross Abstract: LLM rerankers add of the order of $0.2-0.3 per 1,000 queries and about a second of tail latency on top of a graph-augmented dense pipeline such as Hip
arXiv:2609.22158v1 Announce Type: new Abstract: Key-value (KV) caching is essential for efficient autoregressive large language model (LLM) inference, but the cache grows linearly with context length,
arXiv:2609.23215v1 Announce Type: new Abstract: LLM explainers are increasingly attached to autonomous agents as runtime oversight, with operators reading a generated account of the agent's beliefs an
arXiv:2609.22102v1 Announce Type: cross Abstract: Large Language Models (LLMs) are widely used as programming assistants, yet it remains unclear whether and how user's demographic information impacts
arXiv:2609.21686v1 Announce Type: cross Abstract: Privacy leakage in LLM agents is commonly evaluated within individual components such as memory, retrieval, or tool-use pipelines, which makes it diff
I have absolutely never ever 'asked' to stop R&D on LLMs. In fact, I was very supportive of LLM efforts at Meta. Just look up my public advocacy for Galactica (November 2022), and the open sourcing of
jev as a Judge proves to be a cheaper and more precise alternative to LLM as a judge for online evals. great guide from Sean and Daniel on why Jev is great for evals, an experiment vs other LLMs, and
arXiv:2609.19843v1 Announce Type: new Abstract: LLM-based GUI agents increasingly act on behalf of users in digital environments that were designed with human users in mind. These graphical user inter
arXiv:2609.19315v1 Announce Type: cross Abstract: Large language models (LLMs) provide a flexible interface for long-horizon robot planning, but generated plans often fail to respect embodiment constr
arXiv:2609.19213v1 Announce Type: cross Abstract: In this paper, we introduce layer-wise curriculum learning for efficient LLM compression. The proposed method facilitates the knowledge transfer from
arXiv:2609.19515v1 Announce Type: new Abstract: Verifier-based selection improves LLM performance by generating multiple candidate solutions and using a verifier to select the most promising one. Howe
arXiv:2609.19705v1 Announce Type: cross Abstract: Autonomous large language model (LLM) agents are moving rapidly into high-stakes domains, yet existing agentic-AI security studies remain largely doma
TypeSafe’s Jev classifies, scores, and routes without generating text — up to hundreds of times cheaper than an LLM judge. What that changes for evals, confidence routing, and application architecture
arXiv:2609.17532v1 Announce Type: new Abstract: Invasive mechanical ventilation is a lifesaving therapy, but timely, safe discontinuation is essential to preventing extubation failure (EF) and related
arXiv:2609.17989v1 Announce Type: cross Abstract: Large language models (LLMs) now serve as conversational shopping assistants on platforms that also sell advertising. These AI agents face a conflict
arXiv:2604.05012v2 Announce Type: replace-cross Abstract: Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value
arXiv:2609.16053v1 Announce Type: cross Abstract: Long-term memory is essential for LLM-based agents operating over extended interactions. Existing memory systems primarily update memory when new info
TensorRT Edge‑LLM ran Qwen 3.6‑27B on a single NVIDIA Jetson AGX Thor and completed the MLPerf Edge Agentic benchmark in 24 min 36 s—52.33 tokens/s—which is 6.4× faster than the llama.cpp reference (2
arXiv:2609.16232v1 Announce Type: new Abstract: Geospatial artificial intelligence (GeoAI) powered by large language models (LLMs) is expanding the capacity to query, generate, and interpret spatial i