Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2608. 07779v1 Announce Type: new Abstract: Artificial intelligence is changing the task composition of computing work faster than curricula and training typically adapt.
arXiv:2608. 07899v1 Announce Type: new Abstract: Agent systems increasingly expose execution traces, yet telemetry that reveals a failure may still be inadequate for identifying where that failure originated.
arXiv:2608. 07965v1 Announce Type: new Abstract: Gamification is especially effective in learning domains requiring active problem-solving and iterative skill-building, such as cybersecurity education.
arXiv:2608. 08118v1 Announce Type: new Abstract: There are several methods for searching for graphs with prescribed properties, such as SAT solvers and specialized generators.
arXiv:2608. 08055v1 Announce Type: new Abstract: Large language model (LLM) agents that assist users over weeks of conversation must remember what is currently true, not merely what was once said.
arXiv:2608. 08389v1 Announce Type: new Abstract: Long-horizon research agents solve open-ended tasks through iterative retrieval, aggregation, and synthesis, but context grows rapidly while the marginal value of additional evidence often declines.
arXiv:2608. 09577v1 Announce Type: new Abstract: Agent skills, bundles of instructions and resources that an LLM agent loads on demand, form an emerging supply chain where a single poisoned skill can persistently compromise every agent that installs it.
arXiv:2608. 08100v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) enables large language models to classify network flows and generate human-readable incident reports by retrieving semantically similar historical traffic from a vector knowledge base.
arXiv:2608. 08395v1 Announce Type: cross Abstract: Generative AI is shifting digital commerce from browsing toward agentic search, in which consumers delegate product discovery to AI agents.
arXiv:2608. 08814v1 Announce Type: cross Abstract: We present 360CityArena, a benchmark for evaluating the urban exploration capabilities of embodied agents within a photorealistic environment constructed from 360-degree videos.
arXiv:2608. 08996v1 Announce Type: cross Abstract: Quantum low-density parity-check (qLDPC) codes can encode multiple logical qubits using sparse parity checks, yet searching for useful finite-length instances remains a challenging design problem because code performance must be optimized while satisfying practical constraints.
arXiv:2608. 09268v1 Announce Type: cross Abstract: Visual modality has recently been explored as a way to compress textual tokens, including rendering code as images for static code understanding.
arXiv:2608. 09278v1 Announce Type: cross Abstract: GUI agents have advanced rapidly, producing a growing body of frameworks, benchmarks, and applications.
arXiv:2608. 09732v1 Announce Type: cross Abstract: Agent skills are emerging as an important attack surface in LLM-based agent systems.
arXiv:2509. 14474v3 Announce Type: replace Abstract: The debate around Artificial General Intelligence (AGI) remains open due to two fundamentally different goals: replicating human-level performance versus replicating human-like cognitive processes.
arXiv:2510. 27544v3 Announce Type: replace Abstract: Current training paradigms, optimized for long-horizon reasoning trace execution, have made Large Language Models (LLMs) excel at pattern matching and forward simulation of reasoning, but underperform at counterfactual causal understanding and reasoning.
arXiv:2607. 28069v2 Announce Type: replace Abstract: Long-context retrieval and agentic workloads repeatedly reuse the same documents under changing instructions, histories, and document orders.
arXiv:2607. 28432v2 Announce Type: replace Abstract: Intelligence is commonly understood as the ability to acquire and apply knowledge, adapt to unfamiliar situations and solve new problems.
arXiv:2605. 16902v2 Announce Type: replace Abstract: Scientific artifacts such as models and datasets are foundations for research.
arXiv:2605. 12991v3 Announce Type: replace-cross Abstract: LLM-based multi-agent pipelines flip from correct to incorrect answers under simulated peer disagreement at rates we term yield, a vulnerability widely attributed to RLHF-induced sycophancy.