Experiments in Agentic AI for Science
arXiv:2605.26305v1 Announce Type: new Abstract: This paper details two novel frameworks for developing autonomous, agentic AI in scientific workflows. Both systems leverage a hybrid Local Body, Remote
Knowledge catalogue
arXiv:2605.26305v1 Announce Type: new Abstract: This paper details two novel frameworks for developing autonomous, agentic AI in scientific workflows. Both systems leverage a hybrid Local Body, Remote
arXiv:2605.27045v1 Announce Type: new Abstract: The democratization of LLMs has accelerated the generation and circulation of highly fluent disinformation, making traditional syntax-semantic verificat
arXiv:2605.26926v1 Announce Type: new Abstract: Computing legal indicators from normative texts is a key task in legal monitoring and policy evaluation, but presents significant challenges due to the
arXiv:2604.04948v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems depend critically on the quality of document preprocessing, yet no prior study has evaluated PDF
arXiv:2605.27249v1 Announce Type: new Abstract: An effective method of teaching across disciplines is to provide examples of high-quality work. However, an example may be significantly different from
arXiv:2605.26808v1 Announce Type: cross Abstract: Hallucination is a central limitation of large language models (LLMs), and substantial effort has been devoted to understanding and mitigating it. Tow
aside_block <ListValue: [StructValue([('title', 'Summary of today’s news'), ('body', <wagtail.rich_text.RichText object at 0x7fb0f516f910>), ('btn_text', ''), ('href', ''), ('image', None)])]> AI-powe
arXiv:2605.26738v1 Announce Type: new Abstract: Human communication depends on implicit social signals where effectiveness is shaped by tone, context, and conversational norms rather than semantic con
arXiv:2605.27136v1 Announce Type: new Abstract: Uncertainty quantification (UQ) remains a critical challenge in Large Vision Language Models (LVLMs) for reliable predictions and real-world deployment.
arXiv:2605.26741v1 Announce Type: cross Abstract: Inverse design of materials has significantly advanced target-driven formulation optimization, yet existing materials machine learning benchmarks rema
arXiv:2605.26567v1 Announce Type: new Abstract: Clinical practice guidelines (CPGs) encode evidence-based decision logic that clinicians apply by evaluating patient variables, conditional criteria, an
arXiv:2605.26454v1 Announce Type: new Abstract: Large language models (LLMs) learn undesirable properties during pretraining, including dangerous knowledge and toxic text generation. Just as post-trai
arXiv:2605.26678v1 Announce Type: new Abstract: Long-context language models are limited by the memory footprint of the key-value (KV) cache. Existing training-free KV compression methods usually rank
arXiv:2601.21008v3 Announce Type: replace-cross Abstract: Operations Research practitioners debug infeasible models through an iterative process: inspecting Irreducible Infeasible Subsystems ( IIS), i
arXiv:2602.03545v2 Announce Type: replace Abstract: Evaluating AI systems that interact with humans requires understanding their behavior across diverse user populations, but collecting representative
arXiv:2605.26133v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data gr
arXiv:2602.00959v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can be seen as compressed knowledge bases, but it remains unclear what knowledge they truly contain and how far t
arXiv:2602.01518v2 Announce Type: replace Abstract: Despite their importance in model sampling, efficient implementation of Top-k and Top-p algorithms for large vocabularies remains a significant chal
arXiv:2605.26819v1 Announce Type: cross Abstract: We present RAGEAR (Retrieval-Augmented Graph-Enhanced Academic Recommender), a neurosymbolic recommender system for academic course recommendation. RA
arXiv:2605.26784v1 Announce Type: cross Abstract: Standard on-policy reinforcement learning relies on heuristic clipping to enforce trust regions, but this mechanism imposes a severe cost by indiscrim
arXiv:2506.03627v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across various tasks by effectively utilizing a prompting strategy. Howe
arXiv:2512.04868v2 Announce Type: replace-cross Abstract: Knowledge-based conversational question answering (KBCQA) confronts persistent challenges in resolving coreference, modeling contextual depend
arXiv:2605.26548v1 Announce Type: cross Abstract: Large language models (LLMs) now support automated software security tasks, including vulnerability discovery and proof-of-concept (PoC) generation. E
Someone just asked me “What I don’t get is why you see it as some kind of failure that AI labs are now using harnesses and neurosymbolic tools…?” I don’t! As I argued in my newsletter on Claude Code (
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:2605.26161v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are increasingly pretrained on large corpora, raising concerns that evaluation datasets may have been exposed du
arXiv:2605.26849v1 Announce Type: new Abstract: Sampling multiple responses improves language model reasoning, but uniform compute allocation is inefficient: easy questions are over-sampled while hard
arXiv:2602.12833v2 Announce Type: replace-cross Abstract: Longitudinal clinical reasoning over electronic health records requires tracking evolving physiological measurements, laboratory results, and
arXiv:2605.25344v1 Announce Type: cross Abstract: Large language models (LLMs) are dominated by dense linear transformations, whose storage, memory and computational overheads hinder efficient adaptat
arXiv:2605.23977v1 Announce Type: new Abstract: This paper audits benchmark evaluation in clinical-interview depression detection through four complementary probes across DAIC/E-DAIC, CMDC, ANDROIDS,
arXiv:2602.03695v2 Announce Type: replace-cross Abstract: While existing multi-agent systems (MAS) can handle complex problems by enabling collaboration among multiple agents, they are often highly ta
arXiv:2508.19988v3 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved high accuracy on complex commonsense and mathematical problems that involve the composition of multiple r
arXiv:2605.25092v1 Announce Type: cross Abstract: Long-term conversational memory is a retrieval workload classical IR was not built for: the index grows during the query stream, query types shift int
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:2605.26079v1 Announce Type: new Abstract: Modern AI benchmarks operate at a complexity that outpaces traditional verification methods. Tasks authored by domain experts often contain implicit ass
arXiv:2605.24755v1 Announce Type: new Abstract: Speech monologues recorded in naturalistic settings provide opportunities to characterize mental illness phenomenology and detect symptom exacerbation.
arXiv:2512.15605v4 Announce Type: replace Abstract: Autoregressive models (ARMs) currently constitute the dominant paradigm for large language models (LLMs). Energy-based models (EBMs) represent anoth
arXiv:2604.05550v2 Announce Type: replace Abstract: Artificial intelligence research increasingly depends on prolonged cycles of reproduction, debugging, and iterative refinement to achieve State-Of-T
b9326 is a llama.cpp release tagged as 'sync: ggml' with pre-built binaries available for multiple platforms including macOS, Linux, Windows, Android, and openEuler, supporting various CPU and GPU bac
arXiv:2605.24546v1 Announce Type: new Abstract: Process modeling is a sub-domain of Business Process Management (BPM) focused on the translation of process artifacts into formal models. This task trad
arXiv:2605.25186v1 Announce Type: cross Abstract: Formalizing legal provisions promises machine-accessible law and automated legal reasoning, and recent LLMs make it tempting to generate such formaliz
arXiv:2601.05004v2 Announce Type: replace Abstract: Self-destructive behaviors are linked to complex psychological states and can be challenging to diagnose. These behaviors may be even harder to iden
arXiv:2605.25430v1 Announce Type: new Abstract: Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled in
arXiv:2605.24812v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance in code generation, but most methods rely on autoregressive decoding without global planni
arXiv:2605.25977v1 Announce Type: cross Abstract: This paper provides an empirical implementation of the creative quality metric proposed in Calibrated Surprise (Zou & Xu, 2026a). The question this pa
arXiv:2605.11359v2 Announce Type: replace Abstract: Scientific data processing often requires task-specific algorithms or AI models, creating a barrier for domain scientists who need to analyze their
arXiv:2605.24765v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to cybersecurity question answering (QA) for critical tasks such as incident response and vulner
arXiv:2505.18979v2 Announce Type: replace Abstract: Text-to-image (T2I) models can generate not-safe-for-work (NSFW) content, motivating multi-stage safety pipelines with both text and image filters.
arXiv:2605.24018v1 Announce Type: new Abstract: Large language models (LLMs), have shown strong potential in scientific discovery, yet existing methods still face substantial challenges in the design
arXiv:2602.06717v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is commonly based on group sampling to estimate advantages and stabilize policy updates.
arXiv:2602.02605v2 Announce Type: replace-cross Abstract: Evaluating true metacognition in Large Language Models (LLMs) is difficult due to biases and heuristics. This paper presents a framework to me
arXiv:2602.00491v2 Announce Type: replace Abstract: Public health reasoning requires population level inference grounded in scientific evidence, expert consensus, and safety constraints. However, it r
arXiv:2605.25646v1 Announce Type: new Abstract: Autonomous ground robots operating in large-scale outdoor environments require both robust long-range navigation and fine-grained ''last-mile'' explorat
arXiv:2505.11758v2 Announce Type: replace-cross Abstract: Few-shot adaptation of vision-language models remains fundamentally limited by how negative class signals are handled at inference. Existing m
arXiv:2605.24064v1 Announce Type: cross Abstract: Hyper-relational knowledge graphs (HKGs) effectively represent complex facts. While inferring new knowledge in HKGs is a critical problem, current met
arXiv:2605.25254v1 Announce Type: cross Abstract: With unified model-generated images now widespread online, attributing their model of origin offers a path toward transparency and deeper insight into
arXiv:2507.09179v3 Announce Type: replace Abstract: Decentralized finance (DeFi) has introduced a new era of permissionless financial innovation but also led to unprecedented market manipulation. With
arXiv:2507.19219v2 Announce Type: replace Abstract: Overestimation in evaluating large language models (LLMs) has become an increasing concern. Due to the contamination of public benchmarks or imbalan
arXiv:2605.24140v1 Announce Type: new Abstract: Multi-step reasoning remains a central challenge for large language models: single-pass generation is efficient but lacks accuracy; tree-search methods
arXiv:2605.24247v1 Announce Type: cross Abstract: Many automated labeling pipelines classify inputs into categories defined by a written specification, content moderation being a prominent use case. S