The Flow has not summarised this story yet — read it at arXiv Machine Learning.
SeekVLN is a new framework for Vision‑Language Navigation that addresses the problem of agents acting on insufficient evidence, termed Progress Myopia. It combines semantic progress reasoning with active evidence seeking, trained first with Future‑guided Reverse Generation to augment expert trajectories, and then refined via Counterfactual Contrastive Policy Optimization to reward beneficial seeking actions. Experiments on simulated benchmarks show significant gains, improving success rates by 12.7% on R2R‑CE and 7.5% on RxR‑CE, and real‑world tests demonstrate human‑like evidence‑seeking behavior.
arXiv:2606. 11078v1 Announce Type: new Abstract: Various test-time interventions for Computer Use Agents (CUAs), including critic models, have been developed to improve performance through pre-execution action evaluation in complex Graphical User Interface (GUI) environments.
arXiv:2606. 24515v1 Announce Type: new Abstract: Computer-Use Agents (CUAs) execute high-level user goals by perceiving and acting directly within graphical user interfaces.
arXiv:2610.18614v1 Announce Type: new Abstract: Controlling an acting LLM agent means deciding, at each step of a long-horizon task, whether to trust its next action, abstain, or hand off to a human....
AgentHorizon is a benchmark comprising 1,373 computer‑use tasks with instruction‑trajectory pairs collected from 166 hours of human‑recorded activity across three operating systems. The benchmark uses a paired design that swaps instructions to create negative tasks, testing judges’ ability to distinguish successful trajectories from those that completed a similar but incompatible request. Eleven judges were evaluated, with GPT‑5.5 achieving the highest balanced accuracy of 80.9% on the full trajectory subset, while tool‑use benefits some models but harms others, revealing large variability in judges’ performance.
Learn2Play Bench is a new benchmark that tests how well large language model agents learn from experience in unfamiliar, text‑based games with novel or counterintuitive rules. The benchmark provides reproducible feedback, automatic scoring, and varied game instances to evaluate learning across repeated attempts and transfer to new situations. Findings show that retaining full action records aids learning, human players outperform agents, and the choice of harness significantly impacts performance and inference cost.