Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use. Yet the relevant benchmark landscape largely divides into symbolic causal reasoning benchmarks without realistic data analysis or data analysis benchmarks without a principled causal data-generating structure.
arXiv:2607. 07690v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (e.
arXiv:2607. 07370v1 Announce Type: cross Abstract: In embodied intelligence systems, the motion controller serves as the critical bridge between semantic reasoning and physical execution.
arXiv:2607. 06807v1 Announce Type: cross Abstract: While enabling effective collaboration on complex tasks, LLM-based Multi-Agent Systems (MAS) face critical security challenges due to vulnerabilities at the agent and interaction levels.
arXiv:2607. 07379v1 Announce Type: new Abstract: In agentic scientific machine learning (SciML), large language model (LLM) agents can discover surrogate models and select one by an automated score, typically an error metric.
arXiv:2605. 03195v2 Announce Type: replace Abstract: Modern coding agents increasingly delegate specialized subtasks to subagents, which are smaller, focused agentic loops that handle narrow responsibilities like search, debugging or terminal execution.
arXiv:2607. 06760v1 Announce Type: new Abstract: Autonomous systems under partial observability act on beliefs, not raw sensor events.
arXiv:2511. 23347v2 Announce Type: replace Abstract: An associative memory (AM) enables cue-response recall, and it has recently been recognized as a key mechanism underlying modern neural architectures such as Transformers.
arXiv:2506. 08630v3 Announce Type: replace Abstract: A universal controller for any robot morphology would greatly improve computational and data efficiency.
arXiv:2607. 06964v1 Announce Type: cross Abstract: Bridging the gap between human pilot intent and autonomous flight operation is critical for real-world electric vertical takeoff and landing (eVTOL) aircraft deployment.
arXiv:2607. 07676v1 Announce Type: new Abstract: Autonomous AI agents can execute complex tasks with limited human review, yet they often lack the grounded operational knowledge to make their outputs not just executable but correct, secure, and maintainable.
arXiv:2607. 07235v1 Announce Type: cross Abstract: Explainability remains a key issue in reinforcement learning (RL).
arXiv:2605. 15207v2 Announce Type: replace Abstract: Multi-agent LLM systems have shown promise for complex reasoning, yet recent evaluations reveal they often underperform single-model baselines.
arXiv:2602. 21556v2 Announce Type: replace Abstract: When designing compound AI systems, a common approach is to query multiple copies of the same model and aggregate the responses to produce a synthesized output.
arXiv:2607. 07189v1 Announce Type: new Abstract: Vision-language models (VLMs) and agentic AI have shown strong performance on semantic visual tasks, but it remains unclear whether they can handle the physics and inverse problems that underlie computational imaging.
arXiv:2607. 07103v1 Announce Type: new Abstract: Safe autonomous driving requires both rapid responses to common high-risk events and deeper reasoning over rare, extreme long-tail scenarios in traffic safety.
arXiv:2607. 06906v1 Announce Type: new Abstract: Agentic AI development today runs on token maxing: buying capability with tokens -- longer reasoning traces, more turns, wider tool payloads, bigger replayed contexts -- so tokens per task grow faster than task value.
arXiv:2607. 07504v1 Announce Type: new Abstract: Product data scientists often ask LLM-based agents to help with recurring execution tasks such as cleaning data, writing SQL, choosing statistical tests, and formatting results.
arXiv:2607. 07508v1 Announce Type: cross Abstract: Reinforcement learning (RL) is becoming increasingly important for post-training large language models (LLMs).
arXiv:2607. 07695v1 Announce Type: new Abstract: We introduce institutional red-teaming, an evaluation methodology for testing deployment rules in multi-agent AI: hold the agents, objectives, and task state fixed, vary only one rule, and attribute the resulting change in collective behavior to that rule.