Personal-agent memory has largely focused on learning what users know, prefer, and want. However, knowing the user does not necessarily mean knowing what the user and the agent have established together. An assistant's proposal should not become an authorized instruction merely because it is remembered. We introduce Gr...
Jiajun Chen, Xinyue Chen, Yicheng Jiang et al.· 0 citations
Combining pretrained models is a common strategy for building AI systems, whether by aligning a vision encoder with a language model or merging fine-tuned checkpoints. However, finding compatible pairs typically requires costly empirical search, as compatibility is known only after alignment or merging. We propose COMP...
Fabian Gr\"oger, Petar Damjanovi\'c, Maria Brbi\'c· 0 citations
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. That decision needs a per-step confidence signal predicting whether the current rollout will eventually succeed. The agent's own self-reported verbalized confidence is...
Automated post-training transforms pre-trained large language models (LLMs) into models capable of handling diverse domains by automatically constructing and optimizing a recipe of coupled decisions over data sources, data processing, cross-domain composition, and training configuration under a limited experimental bud...
Ruohong Liu, Bohan Tang, Lekang Jiang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Terminal agents have shown strong abilities in complex coding tasks. However, they often struggle to recover from errors during long-running execution (e.g., command errors, faulty implementations), eventually leading to task failures. To this end, we present ReTerm, a self-improving terminal agent trained by learning...
Wei Xie, Kaituo Feng, Shiming Fu et al.· 0 citations
Proactive human-robot collaboration requires autonomous systems to infer not only immediate actions but also the underlying hierarchical intentions governing human behavior. Current deep learning approaches predominantly focus on flat action classification, failing to capture the structural dependencies connecting kine...
Autoresearch systems increasingly undertake entire research projects. In practice, scientific research requires systems to pursue multiple interdependent claims through a continuous, multi-stage workflow and revise experiments as evidence accumulates. Existing evaluations of autoresearch systems, however, typically sco...
Peng Jiang (Tsinghua University), Dongyang Li (Tsinghua University), Quanying Liu (Southern University of Science et al.· 0 citations
Scaling interactive environments is important for training long-horizon agents through reinforcement learning. These environments often require further testing and refinement after initial generation, and correcting defects in a task may also require updating its work context and verifier. However, existing constructio...
Hang He, Lin-Ting Wang, Guan-Ming Liu et al.· 0 citations
Test-time scaling has enabled LLMs to solve increasingly complex reasoning, discovery, and optimization tasks. However, existing approaches often gather observations while seeking evidence for current hypotheses, then generate new hypotheses conditioned on those hypotheses and their associated evidence. This couples ob...
Harshit Joshi, Priyank Shethia, Monica S. Lam· 0 citations
Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers with shorter reasoning. We introduce PaceReasoner, a label-free test-time reinforcement learning framework that uses a model's LONG responses to improve its SHORT-mode accu...
Chang-Guo Jia, Zhi-You Xiao, Xin-Bei Ma et al.· 0 citations
Effective collaboration among large language model (LLM) agents in multi-agent systems requires sharing relevant evidence, requesting missing information, and incorporating teammates'contributions into decisions. Training these behaviors is challenging because final task outcomes provide limited feedback on the value o...
Ke-Ru Chen, Sen-Fon Lin, Ying-Bin Liang et al.· 0 citations
This work introduces Agentic4PDM, a framework that separates adaptive investigation from control over evidence use and supports training-free diagnosis using pretrained representations and labeled references without task-specific diagnostic models, and a standard setting that additionally investigates trained-model pre...
Nam V. Nguyen, Hoa Van Truong, D. HieuD et al.· 0 citations
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
