Great paper on improving memory for AI agents.
Great paper on improving memory for AI agents. NEW paper: Memory Intelligence Agent (MIA) MIA boosts GPT-5.4 by up to 9% on LiveVQA. Quick summary: Most memory-augmented agents treat memory as a stati
Knowledge catalogue
Great paper on improving memory for AI agents. NEW paper: Memory Intelligence Agent (MIA) MIA boosts GPT-5.4 by up to 9% on LiveVQA. Quick summary: Most memory-augmented agents treat memory as a stati
Visually rich documents are especially challenging for agents. Tables, charts, and images often break traditional document pipelines, making complex reasoning difficult📄 So we teamed up with @lancedb
European 78B A3.4B model is now supported by llama.cpp, I am waiting for some GGUFs https://huggingface.co/Aleph-Alpha/Kolibri-1 Kolibri is Aleph Alpha's mixture-of-experts (MoE) reasoning model, with
arXiv:2602.16653v4 Announce Type: replace Abstract: Skills are getting increasingly used in recent agentic frameworks, performing robustly with proprietary LLMs. Yet, their effectiveness for small and
arXiv:2610.22020v1 Announce Type: cross Abstract: Learning from demonstration is an effective strategy for endowing robots with manipulation capabilities but requires training on datasets comprised of
arXiv:2610.21561v1 Announce Type: cross Abstract: Large language models (LLMs) deployed as conversational agents are increasingly expected to follow procedural logic. While factual hallucination has r
arXiv:2610.21389v1 Announce Type: new Abstract: Vision-language-action (VLA) policies commonly place a multi-billion-parameter model inside the feedback loop, repeatedly recomputing task context whene
arXiv:2610.22031v1 Announce Type: new Abstract: Behavioral consistency across repeated executions provides an informative signal for assessing the reliability of large language model (LLM) agents. How
arXiv:2610.22331v1 Announce Type: new Abstract: Deep search agents solve knowledge-intensive tasks through long-horizon, multi-turn interactions, where assigning credit to individual search decisions
arXiv:2610.21176v1 Announce Type: cross Abstract: Large language models (LLMs) reproduce a human working-memory signature on the N-back task: performance declines as memory load N increases, and error
arXiv:2610.21941v1 Announce Type: new Abstract: Recent post-training approaches have shown that self-supervised speech encoders can be adapted to learn a single utterance-level speech attribute throug
arXiv:2606.13220v2 Announce Type: replace Abstract: Large language models (LLMs) are used for technical troubleshooting, where problem descriptions are often incomplete and multiple causes can explain
arXiv:2409.12500v2 Announce Type: replace-cross Abstract: Large language models have become increasingly popular and demonstrated remarkable performance in various natural language processing (NLP) ta
arXiv:2610.22163v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly being adopted as teaching tools in computing education, particularly for developing AI tutors capable of a
arXiv:2610.21308v1 Announce Type: cross Abstract: Consumer phones and wearables increasingly collect physiological time-series data, yet most mobile systems treat these streams as summaries or text ra
arXiv:2610.21040v1 Announce Type: new Abstract: Recursive Self-Improvement (RSI) has gained wide attention for its ability to work with limited data. In a proposer-solver loop, a proposer model writes
arXiv:2610.21287v1 Announce Type: new Abstract: Training-free object removal commonly redirects self-attention away from the target region, but on few-step distilled diffusion models this often leaves
arXiv:2610.20959v1 Announce Type: cross Abstract: Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web. Data agents automate this, but thei
arXiv:2610.20766v1 Announce Type: new Abstract: Imagined speech decoding from EEG offers a promising route toward naturalistic brain-computer interfaces. Traditional closed-set classifiers treat seman
arXiv:2507.19839v2 Announce Type: replace-cross Abstract: The modality gap is intrinsic to multimodal alignment, where embeddings from different modalities remain partially separated in a shared repre
arXiv:2610.21477v1 Announce Type: new Abstract: Medical calculators translate raw patient observations into clinically actionable values and scores. However, applying these calculators directly to fre
arXiv:2504.05607v2 Announce Type: replace-cross Abstract: Despite the success of Large Language Models (LLMs) in long-context tasks, their reliability in recognizing unanswerable questions remains a c
arXiv:2610.21266v1 Announce Type: cross Abstract: Continuous video and clinical records provide complementary information for understanding how patient behavior evolves over a hospital stay. A central
arXiv:2610.21553v1 Announce Type: new Abstract: Addressed conditional memory provides a local surface for post-hoc knowledge injection, but a successful write need not transfer to a new question or pr
arXiv:2610.21320v1 Announce Type: cross Abstract: Detailed captions transfer visual information into vision-language model supervision, but quality is easily conflated with length: long single-pass ou
arXiv:2412.12048v2 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has become a standard approach for parameter-efficient fine-tuning of image diffusion models, with over 200K models train
arXiv:2610.19999v1 Announce Type: new Abstract: Legal-content reproduction requires matching the source exactly in section hierarchy, verbatim text, citations, and amendment spans; a dropped citation
arXiv:2610.20571v1 Announce Type: new Abstract: Long-form agentic video generation must turn a screenplay into shots that remain spatially and temporally consistent across nonconsecutive requests. Pas
arXiv:2610.18330v1 Announce Type: new Abstract: Training business automation agents requires executable tasks that connect a natural-language request to an application state and a verifiable end state
arXiv:2610.16426v1 Announce Type: new Abstract: Automated approval systems let coding agents execute high-risk actions with minimal human oversight by delegating the authorization decision to a classi
arXiv:2610.18818v2 Announce Type: cross Abstract: Pre-trained Large Language Model (LLMs) are effective on many tasks in zero-shot and few-shot settings. For machine translation of low-resource langua
arXiv:2610.19906v1 Announce Type: new Abstract: LLMs have achieved strong performance on chemical prediction benchmarks. However, existing evaluation methods typically provide target entity identity i
arXiv:2606.18831v2 Announce Type: replace-cross Abstract: Long-context reasoning is an essential capability for large language models, particularly when they are deployed as autonomous agents that mus
arXiv:2610.19578v1 Announce Type: cross Abstract: Graph Collaborative Filtering models have achieved remarkable success in recommendation systems. However, they inherently suffer from a catastrophic r
arXiv:2610.18052v1 Announce Type: new Abstract: Long-term memory has become a core component of large language model (LLM) agents. As agents accumulate personal information over long-term use, users i
arXiv:2610.15603v1 Announce Type: new Abstract: Materials synthesis planning (MSP) connects AI-driven materials discovery to experimental realization by proposing precursors, synthesis operations, and
arXiv:2607.11414v2 Announce Type: replace Abstract: Large language models (LLMs) in financial applications fail most consequentially when they are confidently wrong. Hedged, uncertain answers invite s
arXiv:2610.19247v1 Announce Type: new Abstract: Transformers are intuitively considered to be efficient at copying from their inputs. We actually show that the ability of LLMs to copy in context can b
arXiv:2610.16191v1 Announce Type: new Abstract: A model may select the correct answer yet fail to construct it through a sequence of local decisions. We introduce Choice2Seq, a diagnostic benchmark th
arXiv:2610.19343v1 Announce Type: cross Abstract: A training-data quality gate changes both which examples survive within regions of the input space and how training mass is distributed across those r
arXiv:2610.14790v1 Announce Type: new Abstract: Reflective language agents reuse feedback and memory to adapt across tasks without updating model weights. However, existing guarantees for policy selec
arXiv:2610.16050v1 Announce Type: new Abstract: Personality assessment from asynchronous video interviews (AVIs) plays a crucial role in recruitment by enabling standardized and behaviorally grounded
arXiv:2610.20158v1 Announce Type: new Abstract: Self-supervised joint embedding learning aligns representations of augmented views while regularizing their distribution to prevent collapse. Regulariza
arXiv:2610.19849v1 Announce Type: new Abstract: We propose DeltaStreamer, a novel agentic framework for streaming video understanding inspired by how humans observe, remember, and investigate. Streami
arXiv:2610.19306v1 Announce Type: new Abstract: Jailbreak attacks against large language models (LLMs) are evaluated using attack success rate (ASR), which depends on correctly identifying responses t
arXiv:2610.18415v1 Announce Type: cross Abstract: Large Language Models (LLMs) are aligned to human preferences, after pre-training and supervised fine-tuning steps. However, standard RL alignment ste
arXiv:2610.14700v1 Announce Type: new Abstract: Most text-to-SQL benchmarks provide the target database. In a large data catalog, however, choosing the sources is part of the problem: an agent must fi
arXiv:2610.14346v2 Announce Type: replace Abstract: Enterprise customer-support agents increasingly rely on Large Language Models (LLMs) to execute bounded, tool-using workflows. We study this problem
arXiv:2610.20392v1 Announce Type: new Abstract: Speculative decoding accelerates LLM generation through lightweight drafting and parallel verification. It is particularly promising for long inputs, wh
arXiv:2610.16301v1 Announce Type: new Abstract: Self-attention assigns two functions to one mechanism-where to read and how to mix-at the price of O(L^2) training, an O(T) decode state, and position s
arXiv:2610.19785v1 Announce Type: new Abstract: Crash Moment Localization aims to localize the major physical impact that interrupts controlled flight in an onboard first-person-view (FPV) video recor
arXiv:2610.17243v1 Announce Type: cross Abstract: The original EneMonIE proposal describes a Web-based semantic system for continuously monitoring energy trends through targeted information extraction
arXiv:2610.16998v1 Announce Type: new Abstract: Deep search enables language agents to solve complex information-seeking tasks through iterative web exploration. However, developing robust open-source
arXiv:2610.20502v1 Announce Type: new Abstract: Longitudinal electronic health records (EHRs) can reveal disease-progression structure, while useful forecasting requires leakage-controlled discovery,
arXiv:2610.16108v1 Announce Type: new Abstract: Maintaining up-to-date clinical practice guidelines (CPGs) is essential for evidence-based medicine, but rapid evidence growth and complex expert consen
arXiv:2610.15091v1 Announce Type: cross Abstract: Argument structures represent how individual arguments interact within a discourse. However, leveraging these structures to infer meaningful knowledge
arXiv:2610.18272v1 Announce Type: cross Abstract: Autonomous research agents must acquire and reason over evidence within a limited budget. Yet relevant sources can remain uninspected or unused, leavi
arXiv:2610.14552v1 Announce Type: cross Abstract: Protocol specifications rarely justify executable behavior in one place: a transition may inherit its source state from a remote control block, name i
arXiv:2610.17928v1 Announce Type: new Abstract: Recent advances in vision-language models (VLMs) have substantially improved the capabilities of GUI agents, while memory augmentation has emerged as a
arXiv:2610.16231v1 Announce Type: new Abstract: As large language models are increasingly adopted as multi-party communication facilitators, there is a growing demand for agents capable of balancing d