Test-Time Unlearning via Sparse Autoencoder
arXiv:2609.16229v1 Announce Type: cross Abstract: Machine unlearning aims to remove specific knowledge from a trained large language model (LLM) without retraining from scratch. Existing methods modif
Knowledge catalogue
arXiv:2609.16229v1 Announce Type: cross Abstract: Machine unlearning aims to remove specific knowledge from a trained large language model (LLM) without retraining from scratch. Existing methods modif
arXiv:2609.17317v1 Announce Type: new Abstract: The use of LLMs to complete online surveys impacts the validity of survey-based research, but detecting such usage remains underexplored. We introduce a
arXiv:2609.16065v1 Announce Type: cross Abstract: Human activity recognition (HAR) is usually framed as gradient-based training of neural networks. Agentic Heuristic Learning (AHL) Studio explores a c
arXiv:2609.14236v1 Announce Type: cross Abstract: With the rapid proliferation of large language model (LLM)-based systems, AI companions have emerged as conversational agents designed to cultivate em
arXiv:2609.13612v1 Announce Type: new Abstract: Modern AI systems are built on the Transformer architecture, whose core operation, attention, accounts for the majority of computation and memory cost.
arXiv:2609.15054v1 Announce Type: new Abstract: Multi-Agent (MA) systems are effective at solving complex tasks that demand planning, tool use, and the synthesis of evidence from multiple sources. Exi
arXiv:2609.14754v1 Announce Type: cross Abstract: Causal claims about large language model (LLM) internals rest on measurements. Those might include a projection, a cosine, an ablation delta, or an in
arXiv:2609.15561v1 Announce Type: new Abstract: Evaluating the factual correctness of large language models (LLMs) is vital for many applications. But are our evaluation tools themselves trustworthy?
arXiv:2609.14717v1 Announce Type: cross Abstract: Speculative decoding accelerates LLM inference by verifying multiple drafted tokens in parallel, allowing a single target forward pass to accept sever
arXiv:2604.07487v2 Announce Type: replace Abstract: Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineeri
arXiv:2508.02312v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs), now a foundation in advancing natural language processing, power applications such as text generation, machine t
arXiv:2609.14637v1 Announce Type: new Abstract: Large language model agents are increasingly deployed for long-horizon task execution. However, current evaluation paradigms face three major limitation
arXiv:2609.15779v1 Announce Type: new Abstract: Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases. However, data agents face a ch
arXiv:2609.10714v1 Announce Type: cross Abstract: The ambitious requirements of sixth-generation (6G) networks are driving communication systems from reliable bit delivery toward meaning-aware and tas
arXiv:2609.15134v1 Announce Type: new Abstract: Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing safety risks that emerge through ru
arXiv:2609.14770v1 Announce Type: cross Abstract: Generalisations are common in scientific communication, even though they are semantically ambiguous. An automated method is needed to identify and cat
arXiv:2609.15387v1 Announce Type: cross Abstract: Human evaluation provides a direct measure of the quality of LLM-generated web applications. However, fitting human judgments through automated evalua
arXiv:2503.18460v2 Announce Type: replace-cross Abstract: Modelica is a widely adopted language for simulating complex physical systems, yet effective model creation and optimization require substanti
arXiv:2609.13916v1 Announce Type: new Abstract: We present North Small Translate, an open-weight, LLM-based machine translation (MT) model with instruction-following capabilities built on the same fou
arXiv:2609.14144v1 Announce Type: new Abstract: A transformer language model is trained to respond to any prompt, but each deployment asks only a narrow range of questions: a support assistant sees de
arXiv:2609.13760v1 Announce Type: new Abstract: Publishing a research manuscript is a routine yet demanding part of scientific life: time-consuming, stressful, and often uncertain in outcome. Recent a
arXiv:2609.15522v1 Announce Type: new Abstract: Large language models (LLMs) with human-like performance on linguistic tasks have transformed the study of language in neurodiverse conditions. LLMs pro
arXiv:2609.15684v1 Announce Type: new Abstract: Language agents increasingly rely on reusable skills, but post-failure repair is often handled by opaque one-shot reflection: a model generates a skill
arXiv:2609.15361v1 Announce Type: cross Abstract: Effective communication is a cornerstone of distributed intelligence in Multi-Agent Reinforcement Learning (MARL), yet ensuring that generated message
arXiv:2609.13463v1 Announce Type: new Abstract: The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reli
arXiv:2609.15598v1 Announce Type: cross Abstract: Generative recommendation has emerged as a promising end-to-end paradigm for personalized recommendation. However, user preferences continuously evolv
arXiv:2609.13353v1 Announce Type: cross Abstract: Agent skills are reusable units for language-model agents, but their risks emerge through model decisions, user context, tool calls, and execution fee
arXiv:2609.15396v1 Announce Type: new Abstract: LLM-based agents increasingly rely on persistent skills, i.e., reusable procedural prompts, to adapt without weight updates. Existing skill self-evoluti
arXiv:2609.15472v1 Announce Type: cross Abstract: What happens when AI machines express fear? Do humans engage differently depending on how they express it? And what does it take to design for affecti
arXiv:2609.13491v1 Announce Type: new Abstract: The strong performance of AI Agents across an impressive variety of tasks is driving an unprecedented investment in agentic infrastructures, however the
arXiv:2609.13872v1 Announce Type: cross Abstract: As 6G networks transition from theoretical frameworks into operational realities, artificial intelligence (AI) evolves from an add-on optimization too
arXiv:2609.07093v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enables large language models (LLMs) to answer questions by accessing external knowledge and has been widely ad
arXiv:2606.12852v2 Announce Type: replace Abstract: Rapid advances have been made in developing general-purpose embodied agent in environments like Minecraft through the adoption of LLM-augmented hier
arXiv:2609.13073v1 Announce Type: cross Abstract: Recent breakthroughs in LLM-based systems and their abilities in problem solving and coding have allowed progress in the AI for Science paradigm, pote
arXiv:2609.12354v1 Announce Type: new Abstract: Long-term conversational agents must answer user queries by recalling information from extended dialogue histories, yet directly using the full history
arXiv:2511.15015v4 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) has become a practical architecture for scaling LLM capacity while keeping per-token compute modest, but deploying Mo
arXiv:2609.11999v1 Announce Type: cross Abstract: In this study, we examine whether a general shell can outperform specialized tools on enterprise tasks. Shell-based agents have shown strong results i
Repo here- https://github.com/Adudeguyman/ComfyUI-Fantastic-MiniMaxH3-PromptBuilder Alrighty, back again with an update to my (manual, no LLM connected) Fantastic MiniMax H3 Prompt Builder. Yeah it's
arXiv:2609.12317v1 Announce Type: new Abstract: A central question in LLM reasoning is whether reinforcement learning (RL) instills genuinely new capabilities or merely reshapes how existing knowledge
Reasoning from scratch round 3: This time, I cover generating a verifier for... a) ...evaluation (base model versus any future model improvement) b) ...the reinforcement learning with verifiable rewar
arXiv:2609.11115v1 Announce Type: new Abstract: Benchmark researchers and developers of large language models (LLMs) and other AI systems need to find relevant evaluations, locate their benchmark data
arXiv:2609.11176v1 Announce Type: new Abstract: Industrial query-to-agent matching fails when topical relevance is mistaken for executable capability, especially on long-tail and boundary-sensitive re
Hey everyone — I’m building TensorSharp, an open-source LLM inference engine. Here are the latest DeepSeek V4.1 Flash GGUF results using its native ggml_cuda backend. Setup: 8× NVIDIA A40, layer split
arXiv:2609.11008v1 Announce Type: cross Abstract: Decentralized Finance (DeFi) has emerged as a rapidly growing blockchain-based financial service, where market transaction dynamics and underlying sma
I'm a teacher looking into running an LLM locally. I've been using ChatGPT for a lot of this work, so I started looking at Ollama because I understand it's designed to run LLMs locally. That said, I'm
arXiv:2609.10854v1 Announce Type: cross Abstract: Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts aud
arXiv:2609.11030v1 Announce Type: new Abstract: AI agents increasingly act through tools and delegated authority, but general incident repositories rarely capture the mechanisms needed to compare publ
arXiv:2609.11231v1 Announce Type: cross Abstract: This paper presents SurgicalRoomAgent, a voice-interactive multi-agent system for smart operating rooms based on large language models (LLMs). The sys
arXiv:2609.10922v1 Announce Type: new Abstract: Auto-research agents have shown the potential to automate hypothesis generation, experiment execution, and iterative refinement. However, scaling this p
arXiv:2609.10893v1 Announce Type: new Abstract: Recent advances in large language models have transformed human-computer interaction. Despite their fluency, these models often produce texts that are g
arXiv:2603.27771v3 Announce Type: replace-cross Abstract: Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jo
arXiv:2609.11192v1 Announce Type: new Abstract: Soft context compression condenses a context into a few memory tokens that a frozen LLM consumes in place of the raw text, but existing compressors fix
arXiv:2609.10810v1 Announce Type: new Abstract: Minimal-edit Grammatical Error Correction (GEC) is a challenging task for zero- and few-shot prompted Large Language Models (LLMs), which systematically
arXiv:2609.11699v1 Announce Type: new Abstract: On-Policy Self-Distillation (OPSD) has emerged as a popular paradigm for large language model (LLM) self-improvement, allowing models to act as their ow
arXiv:2609.11737v1 Announce Type: cross Abstract: Collective intelligence depends not only on the capabilities of individual members, but also on how those members are organized. Yet artificial multi-
arXiv:2609.11209v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves knowledge-intensive large language model (LLM) applications by conditioning generation on retrieved docu
I’ve been building 'Spomin', a router that replaces context with summaries directly in the KV cache. The goal is to keep long running sessions going without repeatedly stopping for full compaction and
arXiv:2609.10824v1 Announce Type: cross Abstract: Before an LLM agent tackles tasks in a new environment, it can inspect available corpora and tools and construct reusable resources such as indices, s
Astra's launch has produced a strange discourse. The reporting that broke the story framed the model's use of recurrent depth primarily as a safety regression, because it means the model reveals less
Looking for tools to build/run an engine to do STT-LLM-TTS basically. I know how to run all of them separately, and if need be I can build one myself, but I was curious if there is already an open sou