Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2608. 11216v1 Announce Type: new Abstract: World modeling is an unsettled field: architectures, training objectives, and state representations interact in complex ways, and no single recipe dominates across environments.
arXiv:2608. 12273v1 Announce Type: cross Abstract: LLM agents increasingly rely on third-party skills, using natural-language descriptions for selection and instruction bodies for planning.
arXiv:2605. 12236v2 Announce Type: replace-cross Abstract: Fine-tuning pre-trained robot policies with reinforcement learning (RL) often inherits the bottlenecks introduced by pre-training with behavioral cloning (BC), which produces narrow action distributions that lack the coverage necessary for downstream exploration.
arXiv:2608. 11211v1 Announce Type: new Abstract: Conway's 99-graph problem asks whether a strongly regular graph with parameters $\mathrm{srg}(99,14,1,2)$ exists.
arXiv:2608. 11381v1 Announce Type: new Abstract: We study whether the localized numerical operations and integrative judgments of financial analysis benefit from the same form of LLM specialization.
arXiv:2608. 12262v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been growing the capability for scientific writing and collaboration.
arXiv:2608. 11410v1 Announce Type: new Abstract: Offline reinforcement learning (RL) offers considerable promise for optimizing ICU treatment decisions, yet standard evaluation metrics Mean Squared Error (MSE) and Fitted Q-Evaluation (FQE) assess only behavioral imitation and cannot detect Toxic Mimicry, a failure mode in which agents replicate harmful patterns such as treatment withdrawal during comfort-care transitions.
arXiv:2608. 11977v1 Announce Type: new Abstract: Tool-using LLM agents are commonly trained and evaluated in environments where tool calls succeed reliably, yet deployed tools can fail transiently, persistently, or silently.
arXiv:2608. 11683v1 Announce Type: new Abstract: AI agents are increasingly deployed for professional investment research, yet no benchmark captures the complexity of the full investor workflow.
arXiv:2608. 12253v1 Announce Type: cross Abstract: Multi-agent reinforcement learning for human-AI interaction typically relies on a single large language model to simulate user behavior.
arXiv:2608. 11692v1 Announce Type: new Abstract: Autonomous logistics sorting systems (ALSS) are an important industrial application of embodied AI, which requires joint planning over spatially disjoint camera views.
arXiv:2608. 12104v1 Announce Type: cross Abstract: The increasing deployment of autonomous, agentic AI systems challenges traditional accountability mechanisms.
arXiv:2608. 11775v1 Announce Type: new Abstract: Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood.
Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or what it should convey. We show that this gap enables state-corruption attacks, in which attacker-controlled content makes environmental claims beyond the informational authority of its response component and corrupts the agent's perceived environment, making the resulting action appear justified to existing guardrails.
Release: alchemy-utils 0. 1a0 I've long pondered what a database agnostic version of my sqlite-utils Python library and CLI utility might look like.
Modern black-box Image-to-Video (I2V) models offer powerful capabilities in automated content creation, yet their lack of fine-grained control and reliability presents significant challenges in professional workflows. Their inherent stochasticity causes minor variations in textual prompts or hyperparameters to yield drastically different outputs often necessitating inefficient, brute-force trial-and-error processes.
Evaluating security vulnerability detection tools requires benchmark datasets with vulnerability-inducing commits (VICs) - the commits that first introduce vulnerabilities into codebases. VICs are essential for determining the full range of vulnerable software versions.
Enterprise Document Intelligence [Vol. 1 #5nonies] - Nature, plan, execute, synthesize: closing brick 1 with a dispatcher that reads each PDF’s nature and picks the method that fits, fitz, Docling, PaddleOCR, EasyOCR, MinerU or Surya, then folds the outputs into one corpus The post Before Full Agentic RAG: Know How You Decide, and the Parsing Methods You Pick From appeared first on Towards Data Science .
With the increasing complexity of cyber assaults in cloud environments, adaptable security solutions are needed that can support real-time detection and autonomous response. In this paper, we propose a reinforcement learning-based dynamic cyber defense framework.
Natural-language interfaces to enterprise data must translate underspecified requests into governed, executable behavior while controlling invalid queries, policy failures, cost, and nondeterminism. SemPlan Benchmark evaluates this architectural design space with a deterministic synthetic bilingual benchmark containing 1,800 cases in English and Brazilian Portuguese; 1,200 cases form the frozen scientific evaluation subset.