Knowledge catalogue
arXiv:2609.06127v1 Announce Type: cross Abstract: Retrieval-augmented generation is usually formulated as a statistical information-retrieval problem. Graph-based variants add relational structure, bu
arXiv:2609.07255v1 Announce Type: new Abstract: Language-model agents increasingly rely on skills: reusable procedural knowledge for reasoning, tool use, and interaction. Existing work studies how ski
arXiv:2609.10237v1 Announce Type: new Abstract: A graph retrieval-augmented generation pipeline chooses which triples to put in the prompt, a syntax to write them in, an order to write them in, and a
arXiv:2609.08589v1 Announce Type: cross Abstract: Recent large language models can emit task-progress signals that agent frameworks use to decide whether a task should continue or stop, yet whether a
arXiv:2508.15754v2 Announce Type: replace-cross Abstract: Tool use is often assumed to monotonically improve reasoning, where external evidence is expected to help when relevant and be ignored when ir
arXiv:2609.07036v1 Announce Type: cross Abstract: We identify the Flow Moment, a reasoning pattern characterized by sustained, process-confirming verbalizations such as I'm doing, in contrast to the r
arXiv:2609.07046v1 Announce Type: new Abstract: AI has revolutionized various engineering domains, but its impact on semiconductor device design and defect discovery is still limited, due to limited d
arXiv:2609.05881v1 Announce Type: cross Abstract: Developers increasingly run large language models locally by pulling quantized GGUF artifacts from public registries, yet nothing in the distribution
arXiv:2609.09038v1 Announce Type: new Abstract: Reasoning representations are increasingly used as explanations for large language model outputs. Yet they are typically evaluated with model-centric cr
arXiv:2609.06073v1 Announce Type: new Abstract: Federated fine-tuning adapts large language models (LLMs) to decentralized client data, but its scalability in cross-device training is often limited by
arXiv:2609.07876v1 Announce Type: cross Abstract: Recent methods in language model interpretability employ techniques such as sparse autoencoders to decompose residual stream contributions into linear
arXiv:2609.09054v1 Announce Type: new Abstract: Task vectors enable post-training model editing by identifying semantically meaningful directions in weight space, typically computed as the difference
arXiv:2609.04909v1 Announce Type: cross Abstract: Large language models (LLMs) have significantly advanced automated program repair (APR), yet existing evaluations remain largely result-centric and pr
arXiv:2609.04648v1 Announce Type: new Abstract: Reinforcement learning (RL) has become one of the primary paradigms for reasoning enhancement of large language models (LLMs). In particular, Group Rela
arXiv:2609.05224v1 Announce Type: new Abstract: Recent progress in multimodal large language models (MLLMs) has fueled significant enthusiasm in their potential to act as autonomous agents for real-wo
arXiv:2609.05235v1 Announce Type: cross Abstract: Cryptocurrency markets exhibit extreme volatility and non-stationary dynamics that challenge conventional forecasting methods. Although Large Language
arXiv:2609.05059v1 Announce Type: cross Abstract: Whether repeated identical buying questions exhaust a language model's brand recommendations depends on retrieval. Across 300 question-engine cells (5
arXiv:2609.04482v1 Announce Type: new Abstract: Safety alignment is usually posed as a topic-level question: is this subject harmful? Deployments ask a narrower one. A civics tutor and a public-sector
arXiv:2609.04748v1 Announce Type: cross Abstract: Prefix caching, in which a serving engine reuses the key and value tensors of a shared prompt prefix across requests, is enabled by default in the maj
arXiv:2609.05279v1 Announce Type: new Abstract: Production multi-agent systems replace agents constantly, on the assumption that an agent filling a role is interchangeable with any other agent that ca
arXiv:2609.05261v1 Announce Type: new Abstract: Large language model agents increasingly rely on execution traces to master complex interactive tasks. However, current paradigms are bottlenecked by sh
I only use free tiers of these large models to offset compute while my own system runs and for 'different' points of view, since what pops ups suggestions seems to vary a lot sometimes, even when buil
Hello, I'm a bit obsessed with cache management on local LLMs. For the last few days I've been working on cache management on vLLM with my 2x DGX Spark and DeepSeek v4 Flash 0731. I felt something was
I got a lot of ads for meshy recently and went to try it with hilariously bad results. It apparently can't do anything but decorative figurines. I wanted a body shell for an rc car and it just couldn'
arXiv:2601.10187v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have achieved remarkable strides in multilingual translation but are hindered by a systemic cross-lingual verbosi
arXiv:2609.03436v1 Announce Type: cross Abstract: Reasoning traces of large language models are widely read as containing 'breakthrough' moments and early-legible fates. Both readings rest on measurem
arXiv:2606.18388v2 Announce Type: replace-cross Abstract: RL post-training strategies are dataset-dependent and reveal a recurring empirical pattern: capacity parameters accumulate monotonically acros
arXiv:2609.03218v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly use user context such as memory, profiles, and role prompts to personalize their responses. This personalizati
arXiv:2609.02652v1 Announce Type: new Abstract: Leech-lattice vector quantization holds the strongest reported 2-bit quality under its own evaluation protocol. Its kernel decodes one shell; we found n
arXiv:2609.02083v1 Announce Type: cross Abstract: Removing complete transformer layers preserves a standard serving architecture, but existing depth-compression methods can lose substantial quality, a
arXiv:2609.00231v1 Announce Type: new Abstract: Existing research on object hallucination in multimodal large language models (MLLMs) predominantly attributes the problem to language priors such as ov
arXiv:2609.00605v1 Announce Type: cross Abstract: Machine unlearning for large language models (LLMs) often assumes that a pre-defined forget set matches what the model has memorized, but this frequen
arXiv:2609.00310v1 Announce Type: new Abstract: Emotional labor is the effortful management of emotional displays to meet social or professional expectations. Personality traits have been correlated w
arXiv:2609.00762v1 Announce Type: new Abstract: Parameter-efficient fine-tuning is usually framed as a question of how many parameters to update. Under a severe trainable-state budget, however, where
arXiv:2609.00450v1 Announce Type: cross Abstract: Block Quantization (BQ) is a promising approach for efficient deployment of large language models (LLMs), enabling low-precision computation with cont
arXiv:2609.00222v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as judges for subjective tasks, where annotators disagree and the relevant question is not only how a
arXiv:2609.00192v1 Announce Type: new Abstract: Public trust in Autonomous Vehicles (AVs) may depend not only on technical success but also on the fairness of their decision making. While a recent tre
arXiv:2609.01170v1 Announce Type: new Abstract: Large language models exhibit a modular internal organization that mirrors well-studied functional networks of the human brain, but how this organizatio
arXiv:2609.00062v1 Announce Type: cross Abstract: Data contamination undermines the reliable evaluation of large language models (LLMs) on mathematical problem solving. While rewriting-based evaluatio
arXiv:2604.01452v2 Announce Type: replace Abstract: Scientific discovery is slowed by fragmented literature that requires excessive human effort to gather, analyze, and understand. AI tools, including
arXiv:2608.29988v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong reasoning performance, which depends critically on inference-time decisions. Yet these decisions are commonl
arXiv:2608.30141v1 Announce Type: cross Abstract: Preference optimization is widely used to align large language models with human preferences, but preference-data composition may also influence priva
arXiv:2602.01695v2 Announce Type: replace Abstract: Latent reasoning reduces the token-generation cost of chain-of-thought reasoning by replacing explicit intermediate tokens with continuous latent tr
arXiv:2608.31105v1 Announce Type: new Abstract: Users of a deployed language model routinely encounter behaviours that testing almost never surfaces, since deployment puts the model through orders of
arXiv:2608.28794v1 Announce Type: cross Abstract: Our work evaluates the effectiveness of automated methods for solving CAPTCHA challenges commonly encountered in darknet environments. These CAPTCHAs
arXiv:2608.30948v1 Announce Type: new Abstract: LLMs can imitate how people write, which raises concerns about impersonation, trust, and detection in social settings. These concerns are especially imp
arXiv:2608.29978v1 Announce Type: new Abstract: Large language models are increasingly required to generate responses that satisfy multiple competing objectives. Since optimal trade-offs depend on bot
arXiv:2608.30632v1 Announce Type: cross Abstract: Reinforcement learning (RL), particularly RL with Verifiable Rewards (RLVR), has recently emerged as a central paradigm for enhancing large language m
arXiv:2608.30322v1 Announce Type: new Abstract: Professional agent tasks often depend on conventions that are absent from public corpora, yet benchmarks rarely control whether an agent has access to t
arXiv:2608.31102v1 Announce Type: cross Abstract: Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixtu
arXiv:2608.30873v1 Announce Type: cross Abstract: LLMs are increasingly used for interpersonal advice and as tools for studying social behavior across languages and cultures. A common shortcut for eli
arXiv:2505.17537v2 Announce Type: replace Abstract: Large language models (LLMs) often produce incorrect answers with high confidence, yet the factors associated with such overconfidence remain insuff
arXiv:2601.13206v2 Announce Type: replace Abstract: Large Language Models (LLMs) generate text token-by-token in discrete time, yet real-world communication, from therapy sessions to business negotiat
arXiv:2608.29575v1 Announce Type: new Abstract: Large language models are increasingly used to read documents and produce downstream text, creating a provenance problem when the document owner cannot
arXiv:2608.29564v1 Announce Type: new Abstract: Gradient-based jailbreak suffix optimization methods typically update the suffix by retaining the candidate with the lowest current loss. We show that t
arXiv:2608.29930v1 Announce Type: new Abstract: Black-box model attribution is increasingly relevant when large language models (LLMs) are served through relay and reseller APIs. A tempting low-cost s
arXiv:2608.30395v1 Announce Type: new Abstract: As pretraining scaling laws approach saturation, Test-Time Scaling (TTS) has emerged as an important direction for improving reasoning by allocating inf
arXiv:2608.27460v1 Announce Type: new Abstract: Large output embedding matrices create a significant memory bandwidth bottleneck during autoregressive decoding, especially for compact LLMs with large
arXiv:2608.27817v1 Announce Type: cross Abstract: Speech and audio LLMs are often evaluated by asking whether a waveform prompt beats an automatic speech recognition (ASR) transcript. For known closed
arXiv:2608.28300v1 Announce Type: new Abstract: Robotic industrial panel operation requires not only accurate control localization but also compliance with operating procedures, safety rules, and devi