Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2602.00348v2 Announce Type: replace Abstract: Metal implants in MRI cause severe artifacts that degrade image quality and hinder clinical diagnosis. Traditional approaches address metal artifac...
arXiv:2507.21917v2 Announce Type: replace Abstract: Analyzing digitized artworks requires both visual interpretation and deep artistic, contextual, and historical knowledge. We introduce ArtSeek, a m...
arXiv:2606.18558v2 Announce Type: replace Abstract: Motion forecasting is central to visual intelligence: agents must anticipate how objects will move in order to plan actions, reason about physical...
arXiv:2606.14403v4 Announce Type: replace-cross Abstract: Effective modeling of endangered marine mammal species, such as the North Atlantic Right Whale, is critical for balancing marine conservation...
RealControlBench is a new benchmark that evaluates fine‑grained steering of large language models and agents across diverse behavioral targets and interaction settings. It extends beyond isolated generation tasks to include complex, execution‑grounded, multi‑turn agent interactions, covering instruction‑following control, tool‑use decision control, reasoning performance, reasoning length, and safety awareness. The benchmark jointly measures target controllability and capability preservation, testing robustness across prompts, domains, and model architectures, and finds that current steering methods are often unreliable in realistic scenarios.
The paper proposes a layered verification approach for argument graphs generated by large language models (LLMs). It suggests starting with deterministic checks, then using solver-based methods, followed by LLM reviews, and resorting to debate only when uncertainty remains, reserving human judgment for cases no other instrument can resolve. A study on human-annotated graphs with injected defects shows that while LLM reviewers can detect structural issues with high recall, they also produce false positives, exhibit inconsistent verdicts, and are slower than exact checks, underscoring the need for deterministic verification gates.
The paper introduces domain-specific languages (DSLs) as an explicit representation layer to bridge the gap between high-level natural-language abstractions and concrete actions. Experiments on the visually-grounded “Hexagons” task and the “Text2CAD” benchmark show that code generation using a human-curated DSL yields dramatic performance gains, especially at higher abstraction levels, while automatically induced DSLs only partially recover these gains. The study highlights that the right representation can close much of the performance gap caused by abstraction, but that automatically learning such representations remains a challenge.
The paper proposes an autonomous construction system that combines a large language model (ChatGPT‑5) with a reinforcement learning algorithm to control a mobile crane during retaining wall construction. An enhanced soft actor‑critic model plans crane actions, while robot kinematics ensure these actions are executable. The system also uses a custom embedding model to extract relevant construction data and generates progress updates, safety information, and reports.
MedPAO-Assist is an edge‑deployable, agentic AI framework that structures radiology reports from radiologist dictation and voice commands using only about 3.3 GB of RAM and an average latency of 31 seconds on a standard laptop CPU. It supports four imaging modalities—Chest X‑ray, Chest CT, Abdomen CT, and Brain MRI—and operates entirely with a 0.6 B‑parameter small language model, avoiding cloud APIs or high‑end GPUs. The system follows an Extract‑Ground‑Generate pipeline, performing concept extraction, SNOMED‑CT grounding, structured report generation, and a speech‑driven human‑in‑the‑loop correction phase, enabling a fully “no‑touch” reporting workflow that requires no keyboard input or internet connectivity.
MAMath-Bench is a new benchmark that evaluates multimodal mathematical reasoning in multi‑agent systems (MASs). It contains 1,003 problems across 11 categories, multiple difficulty levels, and modalities such as text, images, and audio, with fine‑grained milestone annotations for correctness, reasoning‑process reliability, and robustness to adversarial perturbations. The study finds that while collaboration can improve intermediate reasoning coverage, it does not consistently boost final‑answer accuracy and can increase redundancy, and current systems remain vulnerable to subtle adversarial errors.
The paper introduces SCAMPER, a system that trains a virtual rat model to exhibit realistic movements during both goal-directed tasks and random exploration. SCAMPER employs a variational architecture with two priors—a motion prior for control and a behavior prior for exploration—to generate natural behavior and effectively exploit task structure. The system can learn from sparse rewards, enabling realistic modeling of sparse-reward tasks used in experimental neuroscience.
The paper introduces TURTLE, an Unsupervised Environment Design framework that evolves tool‑use tasks for AI assistants by using a proposer, solver, and feedback generator powered by large language models. TURTLE automatically generates self‑tuning, long‑horizon benchmarks that increase task difficulty, diversity, and failure modes across multiple applications. Experiments on AppWorld, τ‑Bench, and AutomationBench demonstrate significant gains in hard task percentages and broader reasoning challenges.
The paper introduces ComplianceAgent, a legal compliance sub‑agent within the COMPASS multi‑agent framework, which uses a large language model to evaluate texts on a fixed rubric across digital sovereignty, carbon impact, compliance, and ethics. The agent grounds its judgments in a reference legal corpus, and if a text scores at or below a critical threshold, it initiates a corrective chain that includes self‑healing rewrites, a compliance label, an explainability report, and escalation to a human reviewer. The authors evaluate the agent in a Canadian and Quebec context on a corpus of thirteen legal instruments and a hand‑annotated gold standard of fifteen texts, demonstrating perfect separation of conforming versus non‑conforming texts, stable scores under repeated queries, and relevant passage retrieval.
KPHarness is a framework that co‑evolves knowledge and probing to adapt the external execution harness of a frozen vision‑language‑action model. By using recovery knowledge to generate intervention hypotheses and then actively probing to validate them, the system refines both the interventions applied and the probing strategy itself. The approach separates rapid policy execution from a slower research loop that updates the harness only when sandbox evaluations show improvement, enabling cross‑task reuse of validated recoveries and improved performance on Minecraft tasks such as mining, combat, and crafting.
The paper introduces two measurable preconditions—Verifier Strength and Recoverability—to determine when an agent platform can safely allow unattended self‑improvement. Verifier Strength quantifies how closely an automated verifier (often an LLM judge) aligns with a trusted reference, limiting the extent of permissible changes. Recoverability measures how easily a detrimental change can be undone, requiring that the original version be retained and that rollback restores the prior behavior. The authors implemented these concepts on a platform, demonstrating that unattended edits are viable only when both conditions are met, and highlighted failures in verifier consistency and undo reliability through controlled experiments.
The study evaluates whether multi‑agent systems (MAS) outperform single‑agent systems (SAS) when agents interact with users under a written policy on the dual‑control benchmark. Across 7,950 simulated conversations in airline, retail, and telecom domains, the MAS performed worse in 12 of 13 valid cells and tied only once, with a negative average gain of 28 points. Even in scenarios where prior theory predicted a benefit, the MAS lost performance and incurred higher token costs.
arXiv:2610.27813v1 Announce Type: new Abstract: Multi-agent systems rely on communication to complete tasks, and latent communication passes continuous representations to reduce text generation and r...
arXiv:2610.27911v1 Announce Type: new Abstract: Enterprise agents answer questions over workplace records that evolve through team collaboration. As information is shared, corrected, and revised acro...
arXiv:2610.27965v1 Announce Type: new Abstract: Can humans and artificial intelligence cooperate such that their combination yields greater accuracy than either agent alone? This result, termed \emph...
The paper introduces Agent S4, an autonomous system that learns to design and refine user interfaces for computer‑use agents by observing task execution without explicit success labels. By evolving a repository of interfaces through population‑based selection on unseen validation tasks, Agent S4 achieves state‑of‑the‑art performance on OSWorld V2 and significant gains on ScienceBoard, outperforming large commercial models at lower cost. The work demonstrates that interface design can be treated as an agent capability, enabling continuous improvement beyond fixed, hand‑crafted interfaces.