Knowledge catalogue
arXiv:2609.22219v1 Announce Type: new Abstract: Evaluating an aligned language model by reading its answers assumes the answers carry the distinction the evaluator cares about. We introduce LLM endogn
arXiv:2609.24161v1 Announce Type: cross Abstract: As LLM agents increasingly interact with external tools through standardized protocols such as MCP, tool-interface design becomes a critical yet under
arXiv:2609.24259v1 Announce Type: new Abstract: The effectiveness of agent memory ultimately depends on whether the underlying LLM gives each memory in context an appropriate degree of influence over
arXiv:2609.22133v1 Announce Type: new Abstract: In this paper, we show that LLM and human coding are observationally equivalent in terms of annotation quality: recent LLMs agree with expert coders at
arXiv:2609.22200v1 Announce Type: new Abstract: LLM assistants and agentic systems log long multi-turn conversations. AI providers often scan these conversations for Personally Identifiable Informatio
arXiv:2609.23449v1 Announce Type: cross Abstract: Memory systems are becoming a core component of LLM agents, but constructing and maintaining memory remains expensive because it relies on repeated ca
arXiv:2609.23466v1 Announce Type: new Abstract: Long-running LLM agents require memory that persists and evolves across sessions. Text-based memory retrieves and reconstructs past interactions at ever
arXiv:2609.22143v1 Announce Type: new Abstract: Machine learning learns functions: prompt to response, image to caption. What these functions are mathematically remains hard to say. We present a metho
arXiv:2609.21997v1 Announce Type: cross Abstract: LLM agents in social simulation revise their opinions implicitly, in context: how open an agent is to persuasion can neither be specified nor verified
arXiv:2605.06445v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, production
arXiv:2609.21267v1 Announce Type: new Abstract: Production LLM agents are evaluated repeatedly as they evolve, but full agent benchmarks are costly to rerun. We study efficient recurring evaluation fo
Free SemIf this week is useful. Typed outputs + probabilities look like a cleaner way to route agents than parsing LLM text every time. jev is a new type of model - 'decision models' there are a few o
arXiv:2512.06201v3 Announce Type: replace Abstract: We introduce K2-V2, a 360-open LLM built from scratch as a superior base for reasoning adaptation, in addition to functions such as conversation and
lots of them! Reality is that LLM APIs are far from being the best way to do AI for 90% of use cases in the real world (they're too overkill, slow, expensive, hard to control,...). We will discover th
We tested Jev against LLM judges on accuracy, repeatability, latency, and cost to see whether System One models could offer a new approach to agent evaluation. https://x.com/i/article/2101448785255907
arXiv:2609.20620v1 Announce Type: cross Abstract: Autonomous underwater vehicles (AUVs) operating beyond reliable communications must recover from failures without human intervention. We investigate a
arXiv:2603.19375v2 Announce Type: replace-cross Abstract: Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training datase
arXiv:2609.19244v1 Announce Type: new Abstract: Conversational LLM agents increasingly rely on Web search, yet the end-to-end lifecycle of agentic search remains poorly understood. We present the firs
arXiv:2609.20625v1 Announce Type: cross Abstract: Large language model responses are non-deterministic, so failures in LLM agents are hard to reproduce: a failure depends on inference that is not bitw
arXiv:2609.19425v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents fail in a way no tool-selection or tool-security method addresses: they call tools that do not exist an
arXiv:2609.19830v1 Announce Type: new Abstract: Reinforcement learning for LLM agents involves two distinct optimization di- mensions: how environment feedback is exploited within a trajectory, and ho
arXiv:2609.19799v1 Announce Type: cross Abstract: LLM-driven evolutionary search finds programs by launching seeds and iterating each one. Papers report a single budget setting, usually one seed run f
arXiv:2511.22924v3 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based Multi-Agent Systems (MAS) are susceptible to linguistic attacks that can trigger cascading failures across th
arXiv:2602.04620v3 Announce Type: replace Abstract: GRPO-style reinforcement learning (RL)-based LLM fine-tuning algorithms have recently gained popularity. Relying on heuristic trust-region approxima
Yael Grauer / The Verge: Anthropic and other researchers detail how thousands of people were catfished by dating scam apps using LLM-generated replies from Claude and other models — Security researche
arXiv:2609.17943v1 Announce Type: cross Abstract: Long-context LLM inference is bottlenecked by attention, whose repeated KV-cache reads make decoding memory-bound. Self-speculative decoding alleviate
arXiv:2609.18723v1 Announce Type: new Abstract: We introduce Mahalanobis-Ensemble Decoding (ME-Decoding), a novel Large Language Model (LLM) decoding framework that frames candidate token selection as
arXiv:2609.18779v1 Announce Type: new Abstract: Current Mixture-of-Agents (MoA) paradigms generally treat query routing and agent fine-tuning as separate processes, limiting their ability to respond t
I released KaozKit this week, a Swift library for running LLM agents written in JavaScript inside a Mac app. Built from the start to keep everything local. Providers: MLX with Hugging Face model manag
arXiv:2609.18959v1 Announce Type: new Abstract: LLM code-generation systems usually choose a target programming language before decoding and treat that choice as fixed. We show that, for language-flex
arXiv:2609.19072v1 Announce Type: new Abstract: Large language models are increasingly used for content moderation, but most evaluations still report aggregate accuracy on individual benchmarks. We in
arXiv:2602.15868v3 Announce Type: replace Abstract: Large language models (LLMs) exhibit failure modes on seemingly trivial tasks. We propose a formalisation of LLM interaction using a deterministic m
arXiv:2609.16519v1 Announce Type: new Abstract: Scientific research increasingly relies on large, heterogeneous data sources, motivating interest in retrieval-augmented generation (RAG) systems that p
Banger paper from Google Research. This one is on how LLM assistants reason about the people in a user's life. People ask assistants for social advice constantly, and the assistant only hears the user
arXiv:2609.17496v1 Announce Type: new Abstract: LLM assistants are widely used for daily social advice, yet evaluating their social reasoning in such consultation settings remains challenging since (i
arXiv:2609.17419v1 Announce Type: new Abstract: Long-horizon LLM agents must maintain task state across extended sequences of observations, actions, tool calls, and intermediate beliefs. We study thes
arXiv:2609.13559v1 Announce Type: new Abstract: Large Language Models (LLMs) with function-calling capabilities are becoming critical for modern agentic AI systems. Nevertheless, current deployments t
arXiv:2609.15664v1 Announce Type: cross Abstract: Amid the rapid advancement of physical-world intelligence, cloud-edge collaborative large language models (LLMs) have emerged as a promising roadmap f
arXiv:2609.13936v1 Announce Type: new Abstract: Datasets that ship automatically generated feature annotations invite a question rarely asked of them: would a human agree with those labels? This repor
arXiv:2609.15037v1 Announce Type: cross Abstract: Low-rank gradient projection reduces the optimizer-state memory cost of large language model (LLM) pretraining, but the steps and wall-clock time need
arXiv:2609.13734v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in real-world high-stakes applications, effective governance has become essential. Existing
arXiv:2609.13657v1 Announce Type: new Abstract: Traditional recommender systems are typically trained to predict what item users will interact with next, but not why. However, offering personalized ev
arXiv:2609.15172v1 Announce Type: new Abstract: Spatio-temporal traffic forecasting is a fundamental big data analytics task for intelligent transportation systems, where massive urban sensor streams
arXiv:2502.09192v3 Announce Type: replace Abstract: Anthropomorphism, or the attribution of human traits to technology, is an automatic and unconscious response that occurs even in those with advanced
arXiv:2507.01663v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-collocated
arXiv:2609.12896v1 Announce Type: new Abstract: LLM-based agents rely on heterogeneous interaction capabilities to accomplish complex tasks. Existing approaches often distribute these capabilities acr
Deel handles compliance, payroll, and HR questions across 150+ countries. Instead of searching for the answer through an external LLM each time, they fine-tuned small models built on Deel's own compli
arXiv:2510.18019v3 Announce Type: replace Abstract: Multilingual watermarking aims to make large language model (LLM) outputs traceable across languages, yet current methods still fall short. Despite
arXiv:2609.11957v1 Announce Type: new Abstract: An LLM agent acts on the world by emitting actions: shell commands to run, edits to apply. A wrong action does not always fail loudly; it can fail silen
arXiv:2609.12746v1 Announce Type: cross Abstract: Agentic pipelines for structured-query generation are rapidly expanding, but it is unclear which part of the loop produces the gain. We use LAST-CQ --
I must be among an extremely small group of people (n=1?) that have both 1) trained a frontier LLM and 2) designed and synthesized custom viruses in a lab with my own two hands. And I think that the t
arXiv:2609.11190v1 Announce Type: new Abstract: AI shopping assistants increasingly redirect consumer discovery, creating an urgent need for tools that support seller-side competitive decision-making.
arXiv:2609.11677v1 Announce Type: cross Abstract: Self-evolving runtime harnesses can substantially improve the capabilities of large language model (LLM) agents and provide a promising paradigm for o
arXiv:2609.11180v1 Announce Type: new Abstract: Large language model (LLM) coding agents constantly decide whether a version satisfies a constraint such as ^1.2.3 or >=2.0,1.2 means >=1.3.0) traps eve
arXiv:2603.17094v2 Announce Type: replace Abstract: Simulating human conversations using large language models (LLMs) has emerged as a scalable methodology for modeling human social interaction. This
Tiffany Hsu / New York Times: MIT launches the LLM Election Observatory, a dashboard tracking how nearly a dozen AI models tailor responses to political queries during the 2026 US midterms — Artificia
arXiv:2609.10996v1 Announce Type: new Abstract: Verbalized confidence, long dismissed as overconfident, coarse, and prone to round-number clustering, is now the more robust soft-scoring mechanism for
arXiv:2609.08016v1 Announce Type: new Abstract: Multi-agent debate, in which several LLMs exchange arguments before answering, is widely assumed to improve answer quality by surfacing genuine disagree
arXiv:2602.19574v2 Announce Type: replace-cross Abstract: Large-language-model (LLM)-based text-to-speech (TTS) systems can generate natural speech, but most are not designed for low-latency dual-stre
arXiv:2609.08189v1 Announce Type: new Abstract: Dynamic layer routing reduces the inference cost of Large Language Models (LLMs) by learning to skip layers for individual tokens. Existing methods, how