The paper introduces Dual Exam, a framework for evaluating the interaction between Multimodal Agents (MAs) and World Models (WMs). It tests agents under fixed environment responses and world models under fixed action interventions across diverse domains, reporting results for 10 agent configurations on 1,088 items and 15 world‑model configurations on 400 cases. The study finds uneven task performance, with some configurations achieving higher indices, but notes that the predictive value for coupled success remains unclear.
arXiv:2609.15683v1 Announce Type: new Abstract: While In-Context Learning (ICL) enables models to adapt from exemplars without parameter updates, multimodal ICL remains largely underexplored, particu...
Agentic World Modeling (AWM) redefines next-observation prediction as a multi-turn evidence-acquisition task, allowing agents to query a real environment safely and construct observations without mutating shared state. Integrated with trajectory-level test-time scaling, AWM enables parallel exploration over a single shared environment, outperforming single-shot simulation by 40.07% and trained world-model baselines by 12.36% on benchmarks such as τ-bench, AppWorld, and OfficeBench. This approach provides a practical foundation for safe and scalable agentic test-time scaling in shared, non-resettable environments.
arXiv:2609.24308v1 Announce Type: new Abstract: Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, int...
AD-WM is a new action‑discriminative joint‑embedding world model designed for counterfactual model predictive control. It augments residual latent dynamics with action‑recovery regularization based on inverse dynamics and conditional mutual information, while discarding auxiliary heads at test time so that MPC remains unchanged. Experiments on OGBench‑Cube and other simulation environments show substantial gains in hard‑start success and mean success, and zero‑shot transfer to a Franka robot improves pick‑and‑place success from 42.2% to 71.1%.
arXiv:2609.40325v1 Announce Type: new Abstract: As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficient pipelines for identifying anoma...
Visual Language Models (VLMs) excel at describing visible scene content but struggle to reason about dynamic multi-agent interactions, where action semantics depend on coordinated roles and spatial-te...
The paper introduces Debate-Mixture-of-Agents (DMoA), a multi‑agent framework that structures role‑based interactions to mimic iterative diagnostic reasoning in clinical settings. Evaluated on 297 rare disease cases and 1,719 challenging cases, DMoA outperformed a GPT‑4o baseline, improving most likely diagnosis accuracy by 10.21 percentage points and safety rate by 11.36 percentage points. Ablation studies and further analyses revealed that these gains stem from the structured workflow rather than merely adding more models or longer outputs, and that performance benefits are influenced by the chosen structure, base model strength, and token budget.
arXiv:2609.13543v1 Announce Type: new Abstract: LLM agents are predominantly benchmarked on short, single-task trajectories, yet real deployments run for hours under contention, surfacing a different...
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 introduces DoublesEval, a diagnostic framework that uses professional doubles badminton to test visual‑language models’ ability to reason about dynamic multi‑agent interactions. It decomposes rallies into key moments and evaluates models across four dimensions—atomic recognition, intra‑segment composite understanding, cross‑segment causal reasoning, and high‑level tactical abstraction—highlighting specific reasoning failures. The authors also propose TacticCheck, a lightweight consistency checker that improves performance without retraining the models, yet significant gaps remain in tactical reasoning.
WorldOracle is a benchmark that evaluates action‑conditioned world models (ACWMs) by comparing their predicted rollouts to paired real‑world executions. It assesses models across four dimensions—physical state correctness, spatial alignment, key interaction fidelity, and multi‑view coherence—using curated training and evaluation suites that include long, multi‑segment episodes with both successful and failed actions. Experiments on seven ACWMs highlight distinct strengths and failure modes, providing a systematic foundation for advancing manipulation modeling.
The Agent Error Dataset (AED) presents 50,228 error–diagnosis pairs collected from 9,961 source tasks across 33 environments, 19 harness families, and 23 policy models in text‑based agent systems. A five‑stage Agentic Error‑to‑Training (AET) pipeline generates diagnoses and proposed corrections, verifies them against recorded evidence, and creates separate training views for diagnosis and actor recovery. Experiments show that first‑proposal corrections improve verifier pass rates from 18.4% to 51.1%, and fine‑tuning with full‑diagnosis data raises Qwen3‑8B’s exact‑step agreement from 47.2% to 63.6% on a holdout set.