Knowledge catalogue
arXiv:2605.28359v1 Announce Type: new Abstract: Evaluating whether large language model (LLM) agents can profit in capital markets is increasingly framed as end-to-end trading: place an agent in a his
arXiv:2503.11477v2 Announce Type: replace Abstract: Understanding the factors that trigger or prevent undesirable health outcomes across patient subpopulations is essential for designing targeted inte
arXiv:2605.28684v1 Announce Type: new Abstract: Reduced-order models (ROMs) can accelerate high-dimensional dynamical simulations, but their accuracy often deteriorates when online dynamics leave the
arXiv:2605.28613v1 Announce Type: cross Abstract: This paper studies the stability of low-rank implicit regularization in perturbed deep matrix factorization, where the target matrix is corrupted by a
arXiv:2601.01627v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) are increasingly deployed in healthcare field, it becomes essential to carefully evaluate their medical safety
arXiv:2605.28184v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as the standard paradigm for improving reasoning capability of large language models,
arXiv:2605.27914v1 Announce Type: cross Abstract: Subjective evaluation of LLM behavior -- empathy, restraint, calibrated emotional tone -- is hard. Human inter-rater agreement on such qualities satur
arXiv:2605.27400v1 Announce Type: cross Abstract: The rapid uptake of generative artificial intelligence (AI) in higher education is reshaping assessment practices and intensifying concerns around aca
arXiv:2605.27389v1 Announce Type: cross Abstract: We study how conditioning context shapes personalization behavior in a teacher-facing educational recommender system. We compare contextual conditioni
arXiv:2605.27388v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly utilized as proxies for computational social analysis; yet, their ability to faithfully represent the 't
arXiv:2605.28591v1 Announce Type: cross Abstract: The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified tes
arXiv:2605.28137v1 Announce Type: new Abstract: Text-to-image models trained on large-scale data often inevitably ingest unsafe content. While some people observe input-output amplifications, it remai
arXiv:2605.28168v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated promising capability in generating reward functions for deep reinforcement learning (DRL)-based building
okay i think this is a much better visualization of what i mean by 'log-centric agent architecture' babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is t
arXiv:2605.27551v1 Announce Type: new Abstract: The origin of species has been the mystery of mysteries in natural science. By analogy, the origin of synthetic information, we suggest, is the mystery
arXiv:2605.28597v1 Announce Type: cross Abstract: This position paper argues that the AI/ML community should stop overclaiming and retire the label 'positive backdoor,' and instead treat trigger-activ
arXiv:2510.06974v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in user-facing applications, raising concerns that they may reflect and amplify social biases
arXiv:2605.28123v1 Announce Type: new Abstract: Prompt-based verification is widely used to mitigate hallucinations in large vision-language models (LVLMs), yet when it helps remains poorly understood
arXiv:2605.28533v1 Announce Type: new Abstract: We introduce a testing-by-betting framework that leverages predictions on unlabeled data to enhance the power of sequential hypothesis testing. Given li
arXiv:2605.27760v1 Announce Type: new Abstract: Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However,
arXiv:2605.28219v1 Announce Type: cross Abstract: Unsupervised learning methods -- topic modeling, partition-based and density-based clustering -- produce data groupings without human guidance, yet ch
arXiv:2601.21666v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) are a major focus of recent AI research. However, most prior work focuses on static image understanding, wh
arXiv:2605.11325v2 Announce Type: replace-cross Abstract: Every major benchmark for LLM memory systems, LoCoMo foremost, measures whether a model answered correctly, not whether the memory system retr
arXiv:2605.28639v1 Announce Type: cross Abstract: Instruction-based suppression is widely used to prevent language models from generating prohibited content, yet it remains unclear whether suppression
arXiv:2605.27965v1 Announce Type: new Abstract: Reasoning models often generate long traces in which useful self-correction and unproductive revision are hard to distinguish. We study this distinction
arXiv:2601.07648v2 Announce Type: replace Abstract: As Natural Language Generation (NLG) dominates modern NLP, scalable evaluation remains a critical bottleneck. Consequently, LLM-as-a-judge (LaaJ) ad
arXiv:2605.27851v1 Announce Type: new Abstract: Safety benchmark scores provide incomplete evidence of deployment readiness: aligned language models often adhere to rigid rules even when a situational
Completely agree, @hwchase17 ! This is the meta-level breakthrough we've all been waiting for. Self-optimizing loops finally feel production-ready because LangSmith Engine turns evaluation from a manu
arXiv:2605.26827v1 Announce Type: cross Abstract: Recent benchmarks reveal that despite strong reasoning capabilities, large language models (LLMs) still struggle to faithfully apply complex contextua
arXiv:2603.16870v2 Announce Type: replace-cross Abstract: Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabil
arXiv:2602.08586v3 Announce Type: replace Abstract: Multi-agent LLM systems consistently outperform single-agent baselines, yet practitioners still cannot predict which design works for a new task or
arXiv:2605.26637v1 Announce Type: new Abstract: Most existing embodied intelligence methods formulate perception, reasoning, planning, and control within a unified parameterized policy. Yet these capa
This post likely announces or discusses an open-source AI agent framework that incorporates memory and continual learning capabilities, enabling the system to retain information across interactions an
arXiv:2605.26222v1 Announce Type: new Abstract: Understanding the relationship between generalization and privacy remains a central challenge in modern machine learning theory, particularly for deep n
arXiv:2605.27360v1 Announce Type: cross Abstract: Cellular research and development (R&D) is throttled by six structural processes that each consume months of manual engineering work per iteration: (i
arXiv:2605.26103v2 Announce Type: replace Abstract: Structure-from-Motion -- the process of simultaneously estimating camera poses and 3D scene structure from a collection of images -- remains a centr
arXiv:2602.11799v2 Announce Type: replace Abstract: Multi-modal recommendation has gained traction as items possess rich attributes like text and images. Semantic ID-based approaches effectively discr
arXiv:2605.26394v1 Announce Type: new Abstract: Multi-turn Text-to-SQL is central to enterprise analytics yet remains predominantly evaluated in single-turn settings. We introduce EnterpriseMem-Bench,
arXiv:2605.26712v1 Announce Type: new Abstract: Benchmarks that reflect the diversity and complexity of real-world documents are essential for accurately evaluating Automatic Text Recognition (ATR) sy
arXiv:2605.26147v1 Announce Type: new Abstract: Human decision-making is sequential and uncertainty-aware, yet standard neural networks often rely on static, dense forward computation with limited vis
arXiv:2605.27083v1 Announce Type: new Abstract: Counterfactual tuning (CFT) has emerged as a promising paradigm for Large Language Model (LLM) unlearning by training models to generate alternative fic
arXiv:2605.26289v1 Announce Type: new Abstract: Multi-agent tool calling is becoming the dominant interaction pattern for LLM-based systems, yet existing inference frameworks treat each tool call as a
arXiv:2605.26380v1 Announce Type: cross Abstract: Frontier multimodal large language models (MLLMs) have been reported to achieve over 90% accuracy on fine-grained perception benchmarks. However, such
arXiv:2602.12833v2 Announce Type: replace-cross Abstract: Longitudinal clinical reasoning over electronic health records requires tracking evolving physiological measurements, laboratory results, and
arXiv:2605.26655v1 Announce Type: new Abstract: Automated prompt optimization methods (e.g., DSpy, TextGrad) can substantially improve the performance of large language model (LLM), however, their gen
arXiv:2605.24516v1 Announce Type: cross Abstract: Mixed-motive scenarios are ubiquitous in real-world multi-agent interactions, where self-interested agents often defect for immediate rewards, overloo
arXiv:2605.24216v1 Announce Type: cross Abstract: Monitoring autonomous large language model (LLM) agents for covert malicious behavior is challenging due to delayed, context-dependent, and long-horiz
arXiv:2512.05765v2 Announce Type: replace Abstract: In this paper we argue that influential critiques dismissing Large Language Models (LLMs) as a dead end for AGI misidentify the bottleneck: they con
arXiv:2605.25971v1 Announce Type: new Abstract: While AI agents demonstrate remarkable capabilities in reasoning and tool use, they remain fundamentally reactive: they compute responses only after exp
arXiv:2605.24949v1 Announce Type: cross Abstract: Penetration testing is essential to securing modern web infrastructures, yet traditional manual methods struggle to keep pace with their scale and com
arXiv:2605.24657v1 Announce Type: new Abstract: Major LLM platforms deploy models in an inference-only configuration: the model serves requests but never updates per-user weights. Users must repeatedl
arXiv:2603.24254v2 Announce Type: replace-cross Abstract: Real-world time series exhibit temporally structured uncertainty: volatility clusters in turbulent regimes, dissipates in stable periods, and
arXiv:2605.26029v1 Announce Type: new Abstract: We introduce CausaLab, a scalable environment for evaluating interactive causal discovery by LLM agents. Unlike prior evaluations, CausaLab evaluates bo
arXiv:2603.17044v2 Announce Type: replace-cross Abstract: Unified multimodal models share a language model backbone for both understanding and generating images. Can DPO align both capabilities simult
arXiv:2605.24267v1 Announce Type: new Abstract: Human conversation relies heavily on conversational implicature, in which speakers convey meanings that are suggested rather than explicitly stated. Alt
arXiv:2605.24110v1 Announce Type: new Abstract: Coding agents are increasingly used as iterative development partners, but most benchmarks still evaluate one specification followed by one final assess
arXiv:2512.24075v5 Announce Type: replace Abstract: Early lane-change intention prediction is essential for autonomous driving and ADAS, but it remains challenging because lane-changing behavior depen
arXiv:2605.26097v1 Announce Type: new Abstract: Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required repla
arXiv:2507.10644v4 Announce Type: replace Abstract: The Web of Agents (WoA) transforms the document-centric Web into an environment of autonomous agents acting on users' behalf, a vision newly tractab
arXiv:2512.08974v2 Announce Type: replace-cross Abstract: Severe convection produces localized hazards that often require warnings before radar echoes fully reveal storm development. Convective initia