Knowledge catalogue
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:2601.21132v2 Announce Type: replace Abstract: I demonstrate that large language models can infer ethnicity from names with accuracy exceeding that of Bayesian Improved Surname Geocoding (BISG) w
arXiv:2610.21170v1 Announce Type: new Abstract: Agent memory architectures define how LLM agents store and reuse experience across tasks, but they are typically fixed after deployment, limiting their
arXiv:2610.21404v1 Announce Type: cross Abstract: To improve task performance while encouraging desirable response properties, LLM post-training often combines a primary reward (e.g., correctness) wit
arXiv:2610.21983v1 Announce Type: new Abstract: Learning from experience requires recovering reusable knowledge and determining when it applies to a new situation. We introduce OntoAct, a hypothesis-b
arXiv:2610.20927v1 Announce Type: new Abstract: Long-horizon LLM agents rely on context compaction: when the interaction history outgrows the context window, a compressor replaces it with a natural-la
arXiv:2610.21042v1 Announce Type: cross Abstract: Systematic literature reviews follow the PRISMA process of screening scholarly works and extracting evidence from included studies. Deep research tool
arXiv:2610.21791v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong capabilities in complex tasks, including code generation, tool use, and multi-hop question an
arXiv:2610.21029v1 Announce Type: cross Abstract: As autonomous agents become widely deployed, coordinating access to shared computing resources and services will become increasingly important. Recent
arXiv:2610.20926v1 Announce Type: new Abstract: Agent skills turn procedural knowledge into reusable artifacts, allowing LLM agents to accumulate and refine expertise through experience. Building on t
arXiv:2610.20960v1 Announce Type: new Abstract: Safety in agentic systems is inherently sequential: whether an action is safe depends on prior actions, tool outputs, information disclosures, and inter
arXiv:2610.21746v1 Announce Type: cross Abstract: Many collective-action systems are neither fully decentralized nor fully centralized: agents voluntarily organize into institutions that share organiz
arXiv:2610.21304v1 Announce Type: new Abstract: Current value alignment evaluations for large language models (LLMs) heavily rely on output compliance, overlooking whether LLMs maintain value consiste
arXiv:2610.21500v1 Announce Type: cross Abstract: Reusing the attention KV cache across requests is a standard way to cut prefill cost in long-context LLM serving, and production systems increasingly
arXiv:2609.31784v2 Announce Type: replace Abstract: Open-weight models are often released, fine-tuned, aligned, merged, and re-released, making provenance audits ask not only whether checkpoints are r
arXiv:2609.33196v2 Announce Type: replace Abstract: Evaluating large language models (LLMs) relies heavily on benchmark scores, yet aggregate metrics can obscure whether individual items serve their i
arXiv:2610.18083v1 Announce Type: new Abstract: Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives. Intuitively, m
arXiv:2610.19951v1 Announce Type: new Abstract: Agent skills adapt frozen models through editable external instructions. Revising several rules at once makes changes difficult to inspect, while judgin
arXiv:2610.14877v1 Announce Type: new Abstract: Experience-based learning enables large language model (LLM) agents to improve over time by reusing knowledge from past executions. However, existing me
arXiv:2610.19811v1 Announce Type: cross Abstract: LLM workflows and agents rely on a set of binary decisions like allow/block an input, or discard/retain a retrieved document. When human deferral is u
arXiv:2610.20012v1 Announce Type: new Abstract: Chemistry evaluation has moved past multiple-choice probes toward open-ended expert problems, yet the benchmarks that define the current frontier still
arXiv:2610.18567v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for improving Large Language Model (LLM) by intertwining it with other component
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:2610.20483v1 Announce Type: new Abstract: We study how to improve LLM reasoning at inference time without updating model weights or using external reward models. Recent reward-free power-samplin
arXiv:2610.19801v1 Announce Type: new Abstract: An agent that drives an LLM sends the model the same conversation again and again, and each turn adds only a little text at the end. Inference engines r
arXiv:2610.19157v1 Announce Type: cross Abstract: Code generation models are actively being used in professional and educational settings. However, the competence of large language models (LLMs) to ge
arXiv:2610.18880v1 Announce Type: new Abstract: High-throughput perturbation screens increasingly use machine-learning models to predict the effects of gene combinations that were never measured. A di
arXiv:2610.19836v1 Announce Type: new Abstract: Enterprise group chats record project progress, decisions, task ownership, and other organizational information valuable to enterprise agents. Reliable
arXiv:2610.19855v1 Announce Type: new Abstract: As Large Language Models (LLMs) continue to scale, their energy consumption during inference has become a critical concern. While Autoregressive (AR) mo
arXiv:2610.19799v1 Announce Type: new Abstract: Recent work lets LLM agents evolve their own harness, up to the team itself. Yet in human groups, the same abilities achieve different outcomes under di
arXiv:2610.17130v2 Announce Type: new Abstract: Automated alpha factor discovery is critical for modern quantitative research. While large language models (LLMs) have increasingly been integrated into
arXiv:2610.19868v1 Announce Type: cross Abstract: Training LLM agents on long-horizon interactive tasks with reinforcement learning typically relies on human-annotated tasks and reliable verification,
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:2610.16498v1 Announce Type: cross Abstract: Generative Social Simulation (GSS) leverages Large Language Models (LLMs) to create sophisticated personas that define agents with demographics, emoti
arXiv:2604.06138v2 Announce Type: replace-cross Abstract: Long-context audio reasoning is underserved in both training data and evaluation. Existing benchmarks target short-context tasks, and the open
arXiv:2610.19184v1 Announce Type: new Abstract: Harness optimization improves LLMs by refining reusable prompts and scaffolding, yet requires further adaptation for program generation tasks such as te
arXiv:2610.19064v1 Announce Type: new Abstract: Training large language models (LLMs) across geographically distributed and poorly interconnected compute pools or data centers has become a topic of si
arXiv:2610.19185v1 Announce Type: new Abstract: Evaluation of large language models (LLMs) remains largely pre-scientific: it involves many design decisions, with little guidance on how to make them.
arXiv:2610.19822v1 Announce Type: cross Abstract: LLM agents are evolving from a single model calling tools to planners that orchestrate multiple expert models whose capabilities live in distinct weig
arXiv:2610.16140v1 Announce Type: new Abstract: Transportation planning has traditionally required substantial expertise in network modeling, traffic assignment, and optimization. As a result, strateg
arXiv:2610.17840v1 Announce Type: new Abstract: Multi-agent deliberation can improve recognition by criticizing and revising candidate answers, but fixed controls cannot respond to changes in disagree
arXiv:2610.14071v1 Announce Type: cross Abstract: As LLM agents are increasingly deployed in high-stakes enterprise settings, understanding how they handle sensitive information in agentic dialogue ha
arXiv:2610.18877v1 Announce Type: cross Abstract: Time-series language models typically align numerical signals with language using labels, captions, or question-answer pairs. Although such supervisio
arXiv:2610.14956v1 Announce Type: new Abstract: The Model Context Protocol provides a shared interaction substrate for the agentic web, allowing heterogeneous services to expose capabilities through a
arXiv:2610.19762v1 Announce Type: new Abstract: Medical prescribing errors for multimorbid patients, who require complex drug regimens, are a major patient safety concern. These errors often stem from
arXiv:2610.16175v1 Announce Type: new Abstract: Real-world studies (RWS) analyze routinely collected healthcare data, such as electronic health records and insurance claims, to estimate treatment effe
arXiv:2610.19439v1 Announce Type: new Abstract: While LLM-based agent systems have demonstrated remarkable proficiency in reasoning and solving complex real-world tasks, they also come with substantia
arXiv:2606.13349v2 Announce Type: replace Abstract: Effective peer review requires adaptive investigation that responds to evidence emerging from each paper. Existing LLM-based reviewers largely organ
arXiv:2610.18579v1 Announce Type: new Abstract: System One models choose an agent's next action by scoring a supplied set of options in a single pass. This makes them fast and cheap, but when they cho
arXiv:2610.03948v3 Announce Type: replace Abstract: Autonomous driving decision systems must balance safety, efficiency, and social norms in complex traffic interactions. Philosophical and ethical con
arXiv:2606.20235v2 Announce Type: replace-cross Abstract: Academic paper search is a core step in scientific research, and LLM-based search agents are emerging as a promising paradigm for iterative, i
arXiv:2610.19095v1 Announce Type: new Abstract: Chatbot Arena ranks language models with the Bradley-Terry model, which gives each model one score and so assumes Luce's choice axiom. Choice theory pre
arXiv:2610.14966v1 Announce Type: new Abstract: Long-horizon agents must complete workflows in which later activities depend on earlier outputs and changes to shared state. A key challenge for evaluat
arXiv:2610.16412v1 Announce Type: new Abstract: As IT systems grow in complexity, automated agent-driven incident response becomes increasingly critical. A key capability for these agents is summarizi
arXiv:2610.15964v1 Announce Type: new Abstract: A self-evolving agent rewrites its own harness and must decide which rewrites to keep, so its improvement signal is the check a rewrite has to pass. Ver
arXiv:2610.19992v1 Announce Type: new Abstract: Law students are examined through open-text answers: case solutions, essays and memos that apply the law to a set of facts. Such answers are expensive t
arXiv:2610.15710v1 Announce Type: new Abstract: Long-term memory for assistants needs a gate that decides when a new utterance retires an old stored claim. Benchmark labels for this step mark a pair a
arXiv:2610.18216v1 Announce Type: cross Abstract: LLM agents can adapt to task feedback by revising the textual context that guides their behavior, without changing their model parameters. However, tu
arXiv:2507.14843v5 Announce Type: replace-cross Abstract: Recent advances highlight Reinforcement Learning with Verifiable Rewards (RLVR) as a promising approach to enhancing LLM capabilities. However
arXiv:2610.16725v1 Announce Type: new Abstract: Improving an LLM agent requires knowing what to change when it fails. Similar failures can require different fixes, and resolving one problem can expose