Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
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 pre...
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...
arXiv:2610.40758v1 Announce Type: new Abstract: Self-evolving agents rewrite a persistent state from feedback, but it is largely untested whether this lets them learn a rule nobody told them. An agen...
arXiv:2610.40798v1 Announce Type: new Abstract: Web world models increasingly predict the consequences of candidate actions before agents act, yet a plausible predicted future does not necessarily su...
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 inf...
arXiv:2610.42004v1 Announce Type: new Abstract: Multi-turn negotiation remains a challenging problem for large language model (LLM) agents. While LLMs can conduct natural-language dialogue, existing...
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 r...
arXiv:2610.41245v1 Announce Type: new Abstract: Memory has become central to self-evolving LLM agents, which store and retrieve experience from past rollouts to guide future decisions. Existing syste...
arXiv:2610.41639v1 Announce Type: new Abstract: Autonomous inspection of a target spacecraft is typically the initial step in on-orbit servicing. Planning close-proximity observation viewpoints invol...
arXiv:2610.41368v1 Announce Type: new Abstract: Overly restrictive eligibility criteria contribute to widespread enrollment failure in clinical trials, yet published recommendations for how specific...
The paper introduces a protocol for cross‑interface authorization of AI computer‑use agents, ensuring that policy decisions remain consistent across graphical interfaces, command lines, APIs, scripts, and Model Context Protocol servers. It defines a profile‑bounded system that enumerates all effect‑bearing routes, normalizes requests to canonical effects, issues prepare tickets, and re‑verifies all relevant state at commit time, requiring a sink receipt for a committed result. Extensive testing across two runtime mappings produced thousands of traces, with rigorous checks confirming no semantic regressions, mutant rejections, and correct outcome matching.
arXiv:2610.42147v1 Announce Type: new Abstract: Agentic workflows are increasingly shifting towards long-horizon tasks, such as open-ended scientific work, where models benefit from long context wind...
P-ContextBench is a benchmark designed to evaluate how well large language models understand and safely use personal context. It creates realistic, life‑story‑grounded digital humans from U.S. demographic seeds, embedding traits, routines, goals, and constraints in fragmented, evolving synthetic mobile‑app records. The benchmark tests five capabilities—fact recovery, temporal tracking, pattern inference, and safe handling of conflicting requests—using a multi‑stage validation pipeline and 4,810 verified test cases.
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 ReplayRC...
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 examp...
arXiv:2610.40906v1 Announce Type: new Abstract: Recent scientific agents build knowledge recursively by retrieving evidence, constructing an intermediate state, and judging whether that state contain...
arXiv:2610.41358v1 Announce Type: new Abstract: Existing visual preference evaluation relies on costly human annotations or preference reward models, whereas online marketplace transaction prices are...
The paper introduces Zyphra Hierarchical Attention (ZHA), a subquadratic sparse attention mechanism that uses a tree-structured indexer to compress key-value pairs and retrieve a sparse subset of keys during query time. By iteratively deepening the tree, ZHA achieves sublinear routing and attention costs, resulting in overall subquadratic scaling for long-context processing. The method can be applied to existing pretrained models with minimal distillation training, maintains performance on diverse evaluation tasks, and remains robust even with very deep trees.
3D semantic occupancy prediction provides dense geometric and semantic scene representations for autonomous driving, where both high accuracy and low response latency are crucial for safe downstream f...
Reinforcement learning (RL) has improved the capabilities of large language models (LLMs) across a wide range of tasks. However, token-level RL assigns an action's advantage to the entire generated re...