arXiv:2611.23346v1 Announce Type: new Abstract: Long-horizon LLM agents across codebases, web browsers, and enterprise infrastructure rely on an execution harness to move state between the working context, session history, persistent memory, and external environment. While conve…
⏱ Độ trễ thật của tab này: trung bình 6.9 giờ sau khi CVE được công bố (n = 5180, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.22888v1 Announce Type: new Abstract: Vulnerability exploitation tests whether language model agents can develop working exploits from known software flaws. Sequential test-time scaling can improve exploitation performance, but larger budgets do not ensure sustained ex…
arXiv:2508.00910v3 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success in software engineering tasks when trained with executable runtime environments, particularly in resolving GitHub issues. However, such runtime environments are ofte…
arXiv:2611.17515v1 Announce Type: new Abstract: Can sustained gain-loss (valence) framing sway an LLM agent toward market manipulation? We place Gemma 3 12B into the seat of a defendant in the London silver-fixing litigation, in a market simulation built from real case transcrip…
Games are a rich testbed for visual agents, demanding perception, long-horizon planning, and precise control. However, collecting human gameplay is costly, and learning from gameplay videos requires inferring missing actions. Existing datasets also cover a limited range of games,…
Collaboration promises to extend humanoid capabilities beyond what individual robots can achieve. However, realizing this potential requires coordinated whole-body interactions, coherent long-horizon planning, and precise synchronization across robots. We introduce Heave-Ho, a de…
Streaming video generation must sustain quality beyond the training horizon while handling self-generated history and growing cache costs. To address these challenges, we present MovieRoll, a base-to-distilled framework that connects streaming fine-tuning, long-rollout distillati…
arXiv:2611.17696v1 Announce Type: new Abstract: Long-horizon business workflows fail in two ways: errors accumulate as a chain of activities lengthens, and the knowledge an activity needs is written in a different vocabulary from the user's request. We study whether such workflo…
Training coding agents for long-horizon tasks requires environments with verifiable feedback. Existing pipelines often follow a linear process that ends with validation, establishing usability but providing little guidance on improving training value. Recursive self-improvement (…
Frontier post-training follows a common recipe: train one expert per domain with reinforcement learning (RL), then consolidate the experts into one model via multi-teacher on-policy distillation (MOPD). Such consolidation is expensive: the student samples in every environment aga…
arXiv:2611.17806v1 Announce Type: new Abstract: Long-horizon agents increasingly serve as persistent personal assistants across modern web platforms, managing schedules, applications, and multi-step plans over weeks or months. Users often return to an ongoing conversation after …
Long chain-of-thought (CoT) reasoning improves large vision--language models, but visual information often fades during generation, limiting long-horizon multimodal reasoning. Existing methods either re-inject vision at inference or train policies for stronger grounding, but wher…