BiGrounder introduces a bidirectional training paradigm for GUI grounding, enabling models to generate action descriptions from target coordinates during supervised fine‑tuning and to sample semantically consistent instruction variations during reinforcement learning. This cycle‑consistency approach couples semantic quality with grounding success, allowing the model’s own instruction policy to provide continually refreshed reinforcement trajectories. The 4B‑parameter BiGrounder achieves competitive accuracy across five grounding benchmarks, demonstrating the effectiveness of the proposed training paradigm.
arXiv:2610.19100v1 Announce Type: cross Abstract: Constructing robust GUI agents relies on multimodal visual grounding: the ability to precisely map natural language intents to actionable on-screen c...
arXiv:2511. 07332v2 Announce Type: replace-cross Abstract: Building reliable computer-use agents requires grounding: accurately connecting natural language instructions to the correct on-screen elements.
Natural Language Actor-Critic (NLAC) is a new actor‑critic algorithm that trains large language model (LLM) agents by using a generative LLM critic to produce natural‑language feedback instead of scalar rewards. By providing richer, actionable explanations for suboptimal actions, NLAC helps LLM policies improve without relying on random exploration, and it can be trained off‑policy without policy gradients. Experiments on reasoning, web browsing, tool‑use, and dialogue tasks show that NLAC outperforms existing training methods and offers a more scalable and stable training paradigm for LLM agents.
arXiv:2607. 10891v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly shifting toward agents that solve tasks through diverse interfaces, including web and graphical user interfaces (GUIs).
The paper introduces an online reinforcement learning framework for UI navigation on live iOS apps, separating the agent into a Planning component and a UI Grounding model. It employs an LLM-as-a-Judge to supply dense step-level and terminal rewards, and uses PPO with a novel GiGPPO value estimation to stabilize training. Large-scale infrastructure enables concurrent virtual device training, and experiments on UINavBench, iOSWorld, and AndroidWorld show the approach outperforms supervised fine-tuning and terminal-only RL, achieving significant generalization gains and matching state‑of‑the‑art models on real iOS tasks.
LiteGUI is a new framework for training lightweight GUI agents that tackles the long‑horizon, multi‑path nature of GUI interactions. It introduces a two‑stage post‑training pipeline: Guided On‑Policy Distillation, which uses human‑verified multi‑solution action annotations to provide privileged teacher guidance at each state, and Multi‑Solution Dual‑Level GRPO, which combines action‑level supervision with history‑conditioned planning‑quality supervision while handling multiple valid actions. The authors also present a scalable data generation pipeline and the Lite‑Dataset, enabling extensive evaluation across GUI benchmarks and demonstrating substantial performance gains over existing training paradigms.
Reinforcement learning (RL) has improved the capabilities of large language models (LLMs) across a wide range of tasks. However, token-level RL assigns an action's advantage to the entire generated re...
The paper introduces an exploration-guided prompt scaffolding framework for multimodal large language models, dynamically adjusting the prompt distribution during reinforcement learning post-training. It uses an Exploration Potential Score (EPS) derived from KL-regularized policy improvement to assess prompt utility without extra overhead, and a teacher model rewrites low-utility prompts to preserve intent while improving informativeness. Experiments on Geo3K, MMK12, MathVision, and MMMU-Pro show consistent performance gains, up to 9.7% in-domain and over 11% on out-of-distribution benchmarks.
The paper introduces a label‑free test‑time training approach for GUI grounding, leveraging confidence patterns in coordinate tokens rather than full‑sequence confidence. It proposes Confidence‑Anchored Learning (CAL) to filter pseudo‑labels and assign distance‑based binary rewards, and extends this to Confidence‑Anchored Negative Learning (CANL) which optimizes solely on negative samples to avoid noisy positives. Experiments show that CANL‑7B achieves 92.1% on ScreenSpot‑V2 and 33.8% on ScreenSpot‑Pro, improving the base model by 8.9%.
The paper presents CycleGRPO, a reinforcement learning framework that unifies region understanding and localization for multimodal large language models (MLLMs). By treating the MLLM as both actor and critic, the method generates region captions and immediately grounds them back into spatial coordinates, using a token‑level cycle‑consistency reward that obviates the need for textual ground truths. Experiments on SAMTok demonstrate that CycleGRPO can bootstrap region captioning, VQA, grounded dialogue, and referring segmentation simultaneously, achieving consistent performance gains without task‑specific fine‑tuning.
PointRL introduces a verifiable reinforcement learning framework that learns point-level vision‑language grounding from heterogeneous annotation evidence such as bounding boxes, masks, and instance labels. The method converts these annotations into pointing instructions while preserving target supports, instance membership, and set constraints as hidden verifier evidence, which a deterministic checker uses to score predictions. Evaluation on PointArena shows that PointRL improves Qwen3.5‑4B’s accuracy from 56.11% to 65.58%, and similar gains are observed on RoboSpatial, BLINK, and Ref‑Adv benchmarks.
arXiv:2608. 11191v1 Announce Type: cross Abstract: GUI Visual Grounding is a fundamental capability for GUI agents.