Knowledge catalogue
arXiv:2605.27774v1 Announce Type: new Abstract: In-context learning -- performing tasks based on examples given in the prompt -- is an important capability that has emerged in large language models an
arXiv:2605.28721v1 Announce Type: new Abstract: Are LLM-based search agents genuinely searching, or using the web to verify what they already know? We study this question on BrowseComp with three diag
arXiv:2605.27865v1 Announce Type: new Abstract: Matching submissions with suitable reviewers at scale is a growing challenge for major venues, yet existing approaches either rely on coarse proxy signa
arXiv:2605.27825v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure p
arXiv:2605.28769v1 Announce Type: new Abstract: Softmax attention is the cornerstone of modern large language models, but its memory scales linearly and compute quadratically with sequence length. Lin
arXiv:2605.28487v1 Announce Type: new Abstract: Materials process optimization requires reasoning over routes, conditions, tools and causal dependencies, yet most computational formulations flatten sy
arXiv:2605.28459v1 Announce Type: new Abstract: Multimodal manipulation detection aims to simultaneously identify forged image--text pairs and localize tampered regions, yet existing methods typically
arXiv:2605.28791v1 Announce Type: cross Abstract: On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes into dense
arXiv:2605.27981v1 Announce Type: new Abstract: Evaluating the efficiency of algorithmic code requires test cases that expose runtime bottlenecks. Previous methods generate efficiency test cases eithe
arXiv:2605.26252v1 Announce Type: new Abstract: Long-running AI agents need persistent memory. Memory supports learning across sessions, reduces repeated context injection, and enables auditing of pas
arXiv:2605.26612v1 Announce Type: new Abstract: Personalized generation with frozen large language models requires a conditioning signal that is both compact and current. Existing personalization meth
arXiv:2605.26891v1 Announce Type: new Abstract: This paper presents a multilingual customer service self-help corpus comprising 1,122 manually validated documents in Finnish, Danish, Norwegian, and Sw
arXiv:2605.27071v1 Announce Type: new Abstract: Key knowledge for steel-industry volatile organic compounds (VOCs) governance is scattered across unstructured scientific literature, making it difficul
arXiv:2605.26302v1 Announce Type: new Abstract: Long-lived AI agents are increasingly deployed as persistent operational systems, yet they are still evaluated like freshly initialized models. Day-one
arXiv:2605.25901v1 Announce Type: cross Abstract: 3D Visual Grounding (3DVG) is an essential capability for embodied AI, requiring agents to localize objects in 3D scenes based on natural language des
arXiv:2602.17234v2 Announce Type: replace Abstract: Backtesting LLMs on resolved events assumes models reason only from pre-cutoff knowledge, yet pretrained models inevitably leak post-cutoff knowledg
arXiv:2602.22769v3 Announce Type: replace Abstract: Large Language Models (LLMs) are deployed as autonomous agents in increasingly complex applications, where enabling long-horizon memory is critical
arXiv:2605.26112v1 Announce Type: new Abstract: This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and
arXiv:2605.24042v1 Announce Type: cross Abstract: Of 1{,}536 Gaussian release covariances we tested for single-layer hidden-state privacy, zero achieve both moderate utility and moderate privacy again
arXiv:2605.25475v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows line
arXiv:2605.24299v1 Announce Type: new Abstract: Confidence-weighted routing, selective abstention, and ensemble weighting all assume that a model's stated confidence is informative about its capabilit
arXiv:2605.25869v1 Announce Type: new Abstract: Long-term memory is essential for persistent LLM agents, yet prevailing architectures store historical interactions as unstructured, flat text. This unc
arXiv:2601.02144v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) architectures scale large language models efficiently by employing a parametric ``router'' to dispatch tokens to a sp
arXiv:2601.05847v2 Announce Type: replace Abstract: We revisit the problem of constructing interoperable patient digital twins from unstructured electronic health records (EHRs) and argue that the tas
arXiv:2605.25232v1 Announce Type: cross Abstract: Direct Code2Code transformation remains challenging to control because it can preserve surface-level syntax while introducing semantic drift, hidden b
arXiv:2605.24211v1 Announce Type: cross Abstract: Analogies help learners understand unfamiliar concepts by relating them to known concepts. Despite recent advances, large language models (LLMs) conti
arXiv:2602.11243v2 Announce Type: replace-cross Abstract: Modern LLM-based agents and chat assistants rely on long-term memory frameworks to store reusable knowledge, recall user preferences, and augm
arXiv:2605.23382v1 Announce Type: new Abstract: Agentic reinforcement learning (Agentic RL) has achieved strong progress in tasks with clear success signals. However, many real-world agent application
arXiv:2511.16014v2 Announce Type: replace Abstract: Digitisation in the cultural heritage sector has produced large but fragmented repositories of museum collection data, spanning structured catalogue
arXiv:2605.23071v1 Announce Type: new Abstract: Large language models (LLMs) increasingly rely on long-context processing, but expanding context windows introduces substantial computational and financ
arXiv:2605.23220v1 Announce Type: new Abstract: Despite the growing use of world models as decision-making agents, their adversarial robustness remains underexplored due to the lack of dedicated autom
arXiv:2605.22221v1 Announce Type: new Abstract: Backtracking search underlies classical constraint solvers, planners, and theorem provers. Recent transformer-based reasoning systems explore search tre
arXiv:2605.21515v1 Announce Type: new Abstract: LLM prompting is widely used for naturally stated tasks, yet it is unreliable it may succeed on a few test cases but fail at deployment time. We study p
arXiv:2605.22715v1 Announce Type: cross Abstract: As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild.
arXiv:2605.22057v1 Announce Type: new Abstract: Enterprise routers assign queries to expert agents, yet deployed profiles stay static while agents evolve (prompts, tools, models), and developers rarel
arXiv:2603.27355v2 Announce Type: replace-cross Abstract: We present a readiness harness for LLM and RAG applications that turns evaluation into a deployment decision workflow. The system combines aut
arXiv:2605.21102v1 Announce Type: new Abstract: Academic researchers need efficient and reliable methods for collecting high-quality information from trusted sources, but modern tools for AI-assisted
arXiv:2605.21372v1 Announce Type: new Abstract: Data scaling is fundamental to modern deep learning, and grows increasingly critical as autonomous driving shifts to end-to-end learning. Real-world dri
arXiv:2605.20551v1 Announce Type: new Abstract: Visual Place Recognition (VPR) aims to match a query image to reference images of the same place in a large-scale database. Recent state-of-the-art meth
Gated DeltaNet-2 is here. 🚀 🔥 New paper: Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention Gated DeltaNet-2 outperforms KDA and Mamba-3, the latest and best recurrent architectures, hea
arXiv:2605.20948v1 Announce Type: new Abstract: Scaling conditional memory offers a promising way to increase language-model capacity, but existing methods such as Engram learn large memory tables fro
arXiv:2605.20838v1 Announce Type: new Abstract: Several large-scale video datasets have been published these years and have advanced the area of video understanding. However, the newly emerged user-ge
arXiv:2602.14778v3 Announce Type: replace-cross Abstract: Hallucinations -- plausible but factually incorrect responses -- pose a major challenge to the reliability of Large Language Models (LLMs), es
arXiv:2605.19366v1 Announce Type: new Abstract: Environmental science plays a pivotal role in safeguarding ecosystems, a domain driven by large-scale, heterogeneous data. In the big data era, artifici
arXiv:2605.18767v1 Announce Type: cross Abstract: Multi-hop question answering requires aggregating information from multiple documents, a critical capability for knowledge-intensive applications. A f
arXiv:2603.11768v2 Announce Type: replace Abstract: Long-term memory has emerged as a foundational component of autonomous Large Language Model (LLM) agents, enabling continuous adaptation, lifelong m
arXiv:2605.18974v1 Announce Type: cross Abstract: Classifying artworks presents a significant challenge due to the complex interplay of fine-grained details and abstract features that condition the st
arXiv:2605.19752v1 Announce Type: new Abstract: Accurately identifying metabolites i.e. small molecules from mass spectrometry data remains a core challenge in metabolomics, with broad applications in
arXiv:2603.25722v2 Announce Type: replace Abstract: Contrastive vision-language (V&L) models remain a popular choice for various applications. However, several limitations have emerged, most notably t
arXiv:2605.19528v1 Announce Type: new Abstract: 3D localization in Multimodal Large Language Models (MLLMs), including 3D object detection and 3D visual grounding, is fundamentally limited by camera i
arXiv:2605.17561v1 Announce Type: cross Abstract: Issues faced when using software are reported in the form of bug reports. However, many bug reports are invalid, meaning they do not require code chan
arXiv:2605.17965v1 Announce Type: cross Abstract: Bug localization remains a key bottleneck in downstream software maintenance tasks, including root cause analysis, triage, and automated program repai
arXiv:2605.18284v1 Announce Type: cross Abstract: Software repositories accumulate large amounts of unstructured knowledge in commit messages, pull-request discussions, and issue threads, but develope
arXiv:2605.17304v1 Announce Type: cross Abstract: LLM context is not just tokens; it is a set of commitments. Long-running conversations accumulate goals, constraints, decisions, preferences, tool res
arXiv:2605.16676v1 Announce Type: new Abstract: Metacognition-the ability to monitor one's own knowledge state, spot gaps, and autonomously fill them--remains largely absent from modern AI. Here, we p
arXiv:2605.18421v1 Announce Type: cross Abstract: Recent benchmarks for Large Language Model (LLM) agents mainly evaluate reasoning, planning, and execution. However, memory is also essential for agen
arXiv:2505.20914v2 Announce Type: replace Abstract: General object composition (GOC) aims to seamlessly integrate a target object into a background scene with desired geometric properties, while simul
arXiv:2605.18556v1 Announce Type: cross Abstract: Embodied control increasingly requires models to follow compositional language instructions while reasoning over dynamic visual states. However, curre
arXiv:2605.18565v1 Announce Type: cross Abstract: Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may interfere across memories, requiring accura
arXiv:2605.18652v1 Announce Type: new Abstract: Recent GUI agents have made substantial progress in visual grounding and action prediction, yet they remain brittle in long-horizon tasks that require m