Explore documented scientific discoveries, original research and new scientific developments. Search the library by topic, category or date.
arXiv:2610.40932v1 Announce Type: new Abstract: Unlike conventional architectures that treat memory as static pattern storage, the hippocampus organizes experience as ordered sequences and retrieves them through temporally compressed replay spanning prior, current, and anticipated states.
arXiv Computer Science ARRead article →arXiv:2610.41162v1 Announce Type: new Abstract: To accelerate materials discovery, language models must be able to address problems at the research frontier. Yet textbook- and examination-derived benchmarks primarily assess established knowledge, leaving performance on frontier research problems largely untested.
arXiv AIRead article →arXiv:2610.41158v1 Announce Type: new Abstract: Genetic programming (GP) has been widely used to learn scheduling rules for dynamic flexible job shop scheduling (DFJSS). However, trained rules tend to only generalise to tasks of similar scales and distributions, and when task characteristics change, learned rules often suffer significant performance degradation.
arXiv AIRead article →arXiv:2610.41149v1 Announce Type: new Abstract: Agentic systems increasingly gate individual steps with a pointwise judge that scores a response against a criterion. Small language models are attractive for this role because they can be served and specialized efficiently.
arXiv AIRead article →arXiv:2610.41129v1 Announce Type: new Abstract: AI agents increasingly carry out delegated tasks in parallel, with one person overseeing several of them at once. In practice, an agent often lacks information its task requires, such as an unstated preference, constraint, or specification.
arXiv AIRead article →arXiv:2610.41124v1 Announce Type: new Abstract: Agentic LLM assistants must repeatedly decide whether to answer from memory or to call a tool such as web search. Unnecessary searches cost latency and money; missing ones yield confident but unsupported answers.
arXiv AIRead article →arXiv:2610.41114v1 Announce Type: new Abstract: Optimizing a proxy objective can improve human-perceived quality, but the resulting gain can vary with optimization strength. Average proxy-human correlation alone does not reveal how human-perceived quality changes as optimization strength increases.
arXiv AIRead article →arXiv:2610.41112v1 Announce Type: new Abstract: Quantization of Large Language Models (LLMs) has be- coming increasingly important for reducing the computa- tional costs and resource requirements for practical deploy- ment.Growinginterestinthisareahasmotivatedthecommu- nity to move beyond 8-bit quantization towards 4-bit preci- sion, leading to the development of customized 4-bit formats such as MXFP4 and NVFP4.
arXiv AIRead article →arXiv:2610.41107v1 Announce Type: new Abstract: Manifold learning methods like t-SNE and UMAP preserve local neighborhoods, but they do not preserve the ranking of the neighbors inside them. Two embeddings can return the same neighbor set while disagreeing on which point is closest. This loss of order degrades downstream applications that value the order in the embedding.
arXiv AIRead article →arXiv:2610.41100v1 Announce Type: new Abstract: Time-series foundation models (TSFMs) provide zero-shot forecasts for unseen series, but their accuracy varies across datasets. Combining several models can reduce this variability, yet zero-shot deployment provides no target labels for selecting or weighting them.
arXiv AIRead article →arXiv:2610.41090v1 Announce Type: new Abstract: In text-to-SQL and AI-agent analytics, successful SQL execution does not establish semantic correctness under changing business definitions. We study revalidation of fixed queries after changes to refund attribution, tax treatment, eligible populations and exchange-rate dates.
arXiv AIRead article →arXiv:2610.41089v1 Announce Type: new Abstract: Estimating whether a problem is too complex for a large language model (LLM) before the model attempts it can guide model routing, how to allocate test-time compute, and suggest the need for new tools to aid the agent.
arXiv AIRead article →arXiv:2610.41085v1 Announce Type: new Abstract: Payroll-fraud screening requires finding hidden employee--payee links while distinguishing suspicious relationships from legitimate ones. We formulate this problem as inductive link prediction and entity ranking on synthetic human-resources and enterprise resource planning (HR/ERP) graphs, with unseen organizations and a matched benign twin for every planted case.
arXiv AIRead article →arXiv:2610.41081v1 Announce Type: new Abstract: We study the so-called Minimum Red''Blue Separating Set Problem (MRBSSP) which arises from computational geometry. In particular, we propose a compact Set-Cover ILP formulation, safe preprocessing rules, a Greedy Randomized Adaptive Search Procedure (GRASP), and two exact approaches: one is based on Logic-Based Benders Decomposition (LBBD) approach, and the second…
arXiv AIRead article →arXiv:2610.41076v1 Announce Type: new Abstract: An LLM agent that helps a patient get care must do two things. It must reach the correct outcome, and it must follow the necessary procedure. For example, the agent must get the patient's permission before it shares the patient's records. We introduce BABA-Bench, a benchmark of 47 interactive worlds.
arXiv AIRead article →arXiv:2610.41072v1 Announce Type: new Abstract: Security operations centers (SOCs) need to turn terabytes of alerts, logs and flows into trusted, affordable decisions to unveil hidden threats. We present LanG 2.0, an agentic system that detects threats, correlates evidence and writes rules, investigating whether small local models can replace frontier models affordably and safely when structural safeguards, not…
arXiv AIRead article →arXiv:2610.41044v1 Announce Type: new Abstract: The use of large language models (LLMs) to coordinate multi-agent teams raises a fundamental architectural question: whether task allocation should be centralized in a single LLM controller or distributed across autonomous LLM agents, particularly when communication is unreliable.
arXiv AIRead article →arXiv:2610.41040v1 Announce Type: new Abstract: LLM agents serve natural-language requests through tools, data sources, and other agents, and even simple requests often need several interdependent calls. Typically, the LLM picks these calls by trial and error, with no guarantee of an executable plan.
arXiv AIRead article →arXiv:2610.41025v1 Announce Type: new Abstract: When a language-model agent fails a multi-step task, can another model find the decisive mistake and fix it with a single action? We introduce ReplayRCA, a benchmark that scores such diagnoses by intervention rather than by agreement with annotations: the environment is restored to the state preceding the chosen step, the proposed action replaces the agent's own, and…
arXiv AIRead article →arXiv:2610.41018v1 Announce Type: new Abstract: Violet teaming has been proposed as a method to integrate technical, policy, and societal considerations into the evaluation of emerging technologies. Here, we document a pilot expert workshop used to explore violet teaming as a governance methodology for biodefense-relevant AI capabilities and describe observations from the exercise.
arXiv AIRead article →arXiv:2610.40992v1 Announce Type: new Abstract: Managing multiple chronic conditions through diet requires satisfying disease- and medication-specific requirements jointly across meals and days while preserving established eating habits. These requirements are public in clinical guidelines and drug labels, yet turning them into a feasible plan for one person remains difficult for language-model agents.
arXiv AIRead article →arXiv:2610.40985v1 Announce Type: new Abstract: Good decisions often require considering how outcomes will feel. Yet large language models (LLMs) increasingly enter decision workflows, despite little being known about how they map outcomes to feelings or use those mappings in choice. We tested how LLMs anticipated gambling or stock-trading outcomes would feel and whether they incorporated these ratings into choice.
arXiv AIRead article →arXiv:2610.40970v1 Announce Type: new Abstract: Generative audio systems can produce large libraries of personalized bedtime content, but ordinary media objectives (retention, completion, and novelty) are poorly aligned with the goal of supporting a transition toward sleep.
arXiv AIRead article →arXiv:2610.40959v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for personal tasks, yet evaluating their safe use of personal context remains difficult because such contexts are private, fragmented, dynamic, and socially situated. We introduce P-ContextBench, a realistic, verifiable, and scalable benchmark for evaluating personal-context understanding.
arXiv AIRead article →