Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
Large language models (LLMs) and vision-language models (VLMs) are expanding the range of behaviors that can be represented in agent-based simulations, but many contemporary platforms are difficult to...
We present the NeuralNexus Arm, an open, low-cost 6-DOF robotic manipulator built by an undergraduate engineering team, together with the design decisions and debugging experience needed to reproduce...
arXiv:2608.21345v1 Announce Type: new Abstract: Self-refinement, typically structured as generation, critique, and revision, is a widely adopted paradigm for improving LLM generation and serves as a...
The paper introduces the concept of personalized privacy for large language models, allowing user‑specific disclosure preferences to guide information sharing. It presents P3Bench, a benchmark that extends contextual privacy policies with personalized rules, and shows that existing prompt‑based methods often ignore these policies. To improve compliance, the authors propose “Repair”, an inference‑time attention head intervention that aligns model responses with user‑specific privacy rules.
arXiv:2608.21099v1 Announce Type: cross Abstract: Multi-modal object detection is essential for robust scene understanding in challenging conditions, including low-light and adverse environments. Rec...
The paper introduces CRATE, a two‑stage vision‑language model framework that evaluates mobile agents by reasoning about each step’s consequences and aggregating this evidence to assess task completion. It also presents CRATE‑S, an extension that evaluates operational safety. Experiments show CRATE and CRATE‑S outperform existing benchmarks, achieving high F1‑scores on AndroidWorld and MobileRisk datasets.
The paper investigates how agentic systems decide between acting and abstaining, focusing on the fidelity of their reasoning explanations. Using Qwen3‑8B in a multi‑party conversation setting, the authors compare direct decision policies, reasoning policies, supervised fine‑tuning, and reinforcement learning, finding a trade‑off: strong direct policies yield higher performance but no traceable reasoning, while reasoning policies provide an audit trail at the cost of lower recall. The study also uncovers that exposing reasoning can alter the agent’s policy and that common faithfulness metrics may overstate the alignment between reasoning and decisions.
The paper introduces XKV, a latent protocol that enables efficient communication between heterogeneous language models by translating a sharer's key‑value cache into a receiver's context. XKV overcomes limitations of prior methods by jointly pooling both caches, reconciling differing layer depths, and allowing each receiver position to retrieve its own residual in native KV geometry. Across 45 dataset‑model pairings, XKV outperforms previous protocols and text communication while using fewer parameters and achieving faster translation times.
BIPPO (Budget-aware Independent Proximal Policy Optimization) is a multi‑agent reinforcement learning framework designed for energy‑efficient client selection in federated learning (FL) over IoT systems. It addresses infrastructure constraints such as limited resources and device churn, which traditional FL and RL approaches overlook. Evaluated on two image‑classification tasks with non‑IID data, BIPPO improves mean accuracy over non‑RL methods, standard PPO, and IPPO while consuming only a negligible portion of the budget, even as client numbers grow.
arXiv:2608. 20686v1 Announce Type: new Abstract: Many scientific discovery problems require searching combinatorial hypothesis spaces under complex domain constraints.
arXiv:2608.20566v1 Announce Type: new Abstract: AI agents extend large language models from single prompt-response interactions to long-running, goaldirected workflows that issue many model calls, in...
The paper surveys how large multimodal models (LMMs) enhance agentic frameworks that combine perception, memory, reasoning, planning, and action. It examines the integration of multiple modalities—text, images, audio, and video—through delegated, late‑fusion, and early‑fusion architectures, and maps these designs to agent capabilities. The survey also reviews multimodal agentic systems in robotics, web navigation, multimedia content creation, and video understanding, evaluating performance, efficiency, and scalability trade‑offs.
ProofJudge is an agentic large language model that evaluates the quality of formal proofs in Lean 4 beyond mere correctness. It scores proofs on five dimensions—library leverage, automation fit, structural clarity, statement quality, and Mathlib conventions—using tool access to the relevant repository commit. The system was tested on 218 Mathlib declarations, achieving alignment with human reviewers between 63.5% and 80.8% and releasing its harness, dataset, and traces for open research.
ExpertIVS is a framework that uses 14 sociological expert agents to interpret World Values Survey responses, reconstructing individual value systems in a coherent, internally consistent manner rather than simply concatenating survey answers. It introduces a multi‑agent debate mechanism to assess LLM alignment with these value profiles during dynamic interactions. Experiments on 480 individuals from 12 countries show a 90.78% value restoration fidelity and a 5.3% improvement in value generalization over baseline methods, while also demonstrating strong personality discriminability and behavioral consistency.
FL-MAESTRO is a multi‑agent orchestrator that uses three specialized large language model agents to jointly decide the communication topology, per‑client resource allocation, and aggregation rule in each federated learning round. A coordinator merges the agents’ analyses, and a non‑LLM feasibility check validates the decision before execution. By filtering out clients whose updates would never be aggregated, the system eliminates the main source of wasted round energy in volatile edge networks and works across heterogeneous device classes without per‑class energy models, achieving comparable accuracy to the best energy‑aware baseline while reducing wasted energy from over a third to near zero on a non‑IID CIFAR‑10 benchmark.
TRACE is a training-time framework that uses structured radiology reports to guide concept editing, allowing image-only diagnosis during inference. It refines image-derived concepts with a teacher-guided editing mechanism in a malignancy-aware ordered concept space and introduces Strategic Concept Missing Training to handle incomplete annotations. The authors also present BUSC, a benchmark linking images, labels, and structured attributes, and show that TRACE outperforms existing methods on multiple datasets with better cross-domain robustness.
arXiv:2608.21114v1 Announce Type: cross Abstract: Visual world-model agents such as DreamerV3 act through a recurrent latent state rather than a single observation, which weakens frame-wise observati...
arXiv:2608.21055v1 Announce Type: cross Abstract: Collaborative perception extends the sensing range of a single vehicle by fusing observations from nearby agents, which improves the robustness of au...
arXiv:2608.21049v1 Announce Type: cross Abstract: With the progression in open and disaggregated 6G radio access networks, it is expected that the system will be able to host multi-vendors. In order...
arXiv:2608.20974v1 Announce Type: cross Abstract: Video Joint Embedding Predictive Architecture (V-JEPA) learns powerful spatiotemporal representations from video through self-supervised latent featu...