Knowledge catalogue
arXiv:2609.08407v1 Announce Type: new Abstract: In this study, we identify depth-dependent prefix redundancy in final-readout LLM embedding models, notably across representative backbones including Qw
arXiv:2609.07673v1 Announce Type: cross Abstract: Citation-based measures of scientific influence typically treat citations as uniform signals, ignoring the different roles that cited works play in a
arXiv:2609.05764v1 Announce Type: cross Abstract: The key-value (KV) cache is the dominant memory bottleneck in long-context large language model (LLM) decoding: every step reads it entirely, so decod
arXiv:2609.09115v1 Announce Type: new Abstract: Long horizon Large Language Model (LLM) agents rely on external memory systems to preserve user preferences and task knowledge across extended interacti
Nice showcase that interesting LLM work can be done on single GPU! I extended the GPT-2-style code from @rasbt's 'Build a Large Language Model (from Scratch)' so that it was a 6-expert (2 active) mixt
arXiv:2603.23114v2 Announce Type: replace Abstract: A human's moral decision depends heavily on the context. Yet research on LLM morality has largely studied fixed scenarios. We address this gap by in
arXiv:2609.09153v1 Announce Type: new Abstract: Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. Most agents select actions throug
arXiv:2609.05505v1 Announce Type: new Abstract: Systematic reviews require sustained human judgment across thousands of records, yet existing evaluations of large language models (LLMs) typically exam
arXiv:2609.05800v1 Announce Type: new Abstract: Activation steering controls LLM behavior at inference time by adding learned directions to hidden states, but existing methods handle one concept at a
arXiv:2609.06229v1 Announce Type: cross Abstract: Vulnerability discovery is becoming an important ability of large language model (LLM) agents: agents that silently miss real defects leave critical s
arXiv:2609.06974v1 Announce Type: cross Abstract: Large language models achieve strong performance across diverse tasks, but deployment remains costly because of memory, latency, and energy demands. S
arXiv:2609.06815v1 Announce Type: cross Abstract: An open, networked web will allow agents to run frozen models from multiple vendors, keep their history private, and teach each other which tool to ca
arXiv:2609.06941v1 Announce Type: new Abstract: Causal effect estimation asks how an outcome would change under an intervention, and medicine, economics, and public policy all treat it as a foundation
arXiv:2609.07987v1 Announce Type: new Abstract: LLM-based digital twins promise to reduce repeated human data collection by generating person- specific responses, yet existing evaluations provide litt
arXiv:2609.06563v1 Announce Type: cross Abstract: Social deduction games (SDGs) require agents to reason under partial observability by maintaining relational beliefs about hidden roles and team align
arXiv:2609.07966v1 Announce Type: new Abstract: Key--value (KV) cache compression is an effective way to reduce the memory overhead of large language model (LLM) inference, particularly for long-conte
arXiv:2609.05820v1 Announce Type: new Abstract: We study adaptive routing of prompts to large language model (LLM) experts to maximize response quality in an online setting with limited feedback. We f
Q2D-Web uses agent citations, production web rankings, and a combined set expanded with LLM judgments. These three relevance sets reduce false negatives and reliance on a single labeling pipeline, whi
arXiv:2507.18073v2 Announce Type: replace Abstract: Deploying large language models (LLMs) is challenging due to their massive parameters and high computational costs. Ultra low-bit quantization can s
arXiv:2609.05911v1 Announce Type: cross Abstract: Long-horizon LLM agents interact with untrusted content, persistent memory, external state, and sensitive tools. Existing analyses often characterize
arXiv:2609.04343v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for consequential decisions, making their explanations an important tool for auditing model behavior.
arXiv:2609.04915v1 Announce Type: new Abstract: Many long-horizon LLM deployments face tight prompt budgets: latency, cost, and context limits make full-context prompting impractical as interaction le
arXiv:2609.05269v1 Announce Type: cross Abstract: LLM agent systems increasingly combine provenance tracking, authorization, policy enforcement, protocol adapters, and execution controls. However, ind
arXiv:2609.04749v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems have experienced rapid growth in recent years. Despite their promise, such systems remain fragile,
arXiv:2609.04570v1 Announce Type: cross Abstract: LLM-based code generation fails when correctness depends on execution-dependent coupling: the meaning of one routine is defined by the runtime behavio
// Evaluating and Improving LLM Self-Modeling // Really interesting paper. Can a model answer questions about its own behavior? The questions are deliberately verifiable, such as whether a particular
arXiv:2609.04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every
arXiv:2607.15957v2 Announce Type: replace Abstract: Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as s
It’s going to be so funny when a bridge collapses and hundreds die because it turns out an LLM did the design for the whole thing or even a part of it over a CAD application’s MCP server By funny I me
arXiv:2609.04866v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) create opportunities to enrich simulation-based energy policy analysis, particularly by supporting struc
arXiv:2609.04382v1 Announce Type: cross Abstract: We present a systems-security case study of a two-node split-LLM training system whose privacy evaluation passed while leaving an observable channel u
arXiv:2609.04270v1 Announce Type: cross Abstract: Multi-agent LLM pipelines increasingly assign roles, including execution and verification, to models of different capability tiers. This is done becau
arXiv:2609.05370v1 Announce Type: cross Abstract: Decompilation recovers high-level source from compiled machine code and serves as a foundation for security tasks such as vulnerability detection and
Hello everyone. I felt current LLM benchmark harnesses hand you headline numbers but offer no tooling to see how models actually answered each question (they dump everything to a JSONL or Parquet file
“The expected value of a fully LLM-generated, non-human-reviewed patch is a net-negative by a considerable margin.” 🦔AI can only fix security vulnerabilities 26% of the time. Researchers at 1Password
Otaku is an LLM frontend, primarily designed for roleplay, an alternative to SillyTavern and the like. However, It also works for general-purpose chat with local backends (including Ollama) or cloud m
arXiv:2609.03221v1 Announce Type: new Abstract: Counterfactual audits are the standard tool for checking whether a clinical agent treats demographically distinct but clinically identical patients diff
arXiv:2512.09108v2 Announce Type: replace-cross Abstract: Agentic AI systems built on large language models (LLMs) offer significant potential for automating complex workflows, from software developme
Moving Large Language Models (LLMs) from experimental prototypes into enterprise production exposes a critical truth: your infrastructure dictates both your performance ceilings and your unit economic
arXiv:2609.02889v1 Announce Type: new Abstract: A growing body of work improves frozen large language models (LLMs) as agents by evolving their harness: the textual scaffolding around the model, inclu
Jennifer Pattison Tuohy / The Verge: Anker unveils the Eufy MindBase, a local AI hub for its cameras that runs an on-device, Anker-developed LLM, with a dedicated AI chip and up to 48TB of storage — T
arXiv:2609.02093v1 Announce Type: new Abstract: To address the sequential and evolving nature of time series, the Online Time Series Forecasting (OTSF) task has been extensively studied in multiple do
arXiv:2609.01976v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly embedded in organizational work, yet their errors often pass human review. Prior research locates such f
arXiv:2609.01971v1 Announce Type: new Abstract: AI is rapidly advancing neuroscience, yet many laboratories fail to fully unleash its potential due to significant interdisciplinary barriers. While pre
arXiv:2609.01615v1 Announce Type: new Abstract: Personalizing a frozen large language model (LLM) to individual users is often framed as a meta-learning problem in prompt space: each user is a task, a
arXiv:2602.10118v2 Announce Type: replace Abstract: Peer review is central to scientific quality, yet reliance on simple heuristics, namely lazy thinking and non-specific critiques, has threatened rev
sorry for the radio silence folks - got sucked into extreme LLM psychosis. but i can confidently say we have crossed over into a new age of AI Engineering and we are never, ever, looking back. this is
Speculative decoding speeds LLM inference by letting a lightweight draft model propose multiple tokens that the larger target model verifies in parallel, reducing decoding iterations while preserving
arXiv:2609.00662v1 Announce Type: new Abstract: A multi-model language service must route each request while preserving workload-level budgets for compute, latency, memory, or monetary cost. Two featu
arXiv:2609.00487v1 Announce Type: cross Abstract: Frontier language models that refuse harmful single-turn prompts often comply when the same intent is reached gradually over many turns, making multi-
This was my first serious attempt at tuning a local LLM. I started because Qwen3.8-27B IQ3 was fast on my RTX 5080 but the coding quality disappointed me, and the Q4 profiles I tried in LM Studio were
I'm looking for a small LLM to act as a Linux command assistant. I will use llama.cpp. use case: - User asks in natural language. Model outputs only the shell command - Should work well with no reason
arXiv:2510.13302v4 Announce Type: replace-cross Abstract: Computational stylometry studies writing style through quantitative textual patterns, enabling applications such as authorship attribution, id
arXiv:2609.00958v1 Announce Type: new Abstract: We target practical anonymization of Persian customer chats by training a compact NER model from LLM-labeled supervision and selecting the best labeler
arXiv:2609.00710v1 Announce Type: cross Abstract: An LLM application often sells or internally allocates several service products: a small or premium model, a short or long token cap, and possibly mul
arXiv:2609.01591v1 Announce Type: new Abstract: AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for w
arXiv:2609.01210v1 Announce Type: cross Abstract: Safety benchmarks for large language models often assess the risk of a user query, although the outcome of question answering depends on whether the r
arXiv:2607.09600v2 Announce Type: replace Abstract: Enhancing the reasoning capabilities of large language model (LLM) agents requires effective orchestration of diverse expert models and tools. Howev
BenchMIRT is a new method for auditing LLM benchmarks question by question, revealing which capabilities they actually measure and helping researchers build smaller, more focused, and easier-to-interp
arXiv:2608.25937v2 Announce Type: replace Abstract: Multi-agent systems (MAS) sometimes already have the potential to answer correctly, but still report a wrong answer. Explaining this outcome is diff