…Memory-Augmented Self-Evolution for GUI Agents (2026) Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents (2026) Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement Learning…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Deep research agents have demonstrated remarkable capabilities in complex information-seeking tasks, yet this power comes at a steep computational cost. Driven by accuracy…
…AI-generated summary Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, in complex tasks, GRPO frequently suffers…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Mastering terminal environments requires language agents capable of multi-step planning , feedback-grounded execution , and dynamic state adaptation . However, training such agents is currently…
…agentic LLMs. We further annotate scene-level procedural rules and object-level pose alignments to enable semantically aligned 3D ground truths and automated scene modification. We demonstrate LychSim's capability across multiple…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI…
…In this work, we investigate whether CS capabilities learned from a limited set of seen language pairs can generalize to unseen language pairs through model merging and domain generalization methods. Our experiments…
…AutoMedBench provides the workflow-aware evaluation of LLM agents in AutoResearch tasks, and covering wild range of tasks from segmentation, image enhancement, VQA, report generation and lesion detection 🤔 What makes AutoMedBench…
…We hypothesize that the visual localization capability can be internalized into the textual CoT and that the mandatory explicit grounding introduces unnecessary interference with the model's primary objective of answer prediction…
…We first find that the modern diffusion model where the LLM/VLM serves as the encoder can inherit its encoder's in-context capabilities. This enables us to make the training as…