Agentic process evidence
The way software gets built is changing dramatically. AI agents now create pull requests, select dependencies, refactor codebases, interpret test failures, and execute infrastructure changes across…
generative-ai
MLINFO COLLECTION
AI Agent
ツール利用、計画、マルチエージェント、コード実行などエージェント実装に関係する情報です。
記事一覧
9 / 27Hybrid AI Patterns: Thirteen Ways to Couple Language Models with Rules, and How to Choose Among Them
Language models handle text well, and rule engines give conclusions with proofs. Systems that combine the two are usually described by example, and the same coupling turns up under different names in…
computer-vision
Segment Anything Model Based Context Guided Mamba Unet for Medical Image Segmentation
Medical image segmentation is crucial for clinical diagnosis and treatment planning, requiring both global contextual understanding and fine-grained structural precision. While the Segment Anything…
deep-learning
Deep Reinforcement Learning for Blind Passive Beamforming in RIS-Assisted MIMO Systems
Reconfigurable Intelligent Surfaces (RIS) are a promising solution for improving millimeter-wave (mmWave) communications by controlling signal propagation. Yet, selecting the optimal RIS…
reinforcement-learning
Long-Term Agent Memory through Complementary Curation and Consolidation
Long-horizon dialogue agents require effective memory systems to recall facts, events, and relationships from interaction histories. In this work, we propose a hybrid-memory architecture comprising…
machine-learning
PAPERBENCHX: Can AI Reproduce Science Across Disciplines?
Before AI can be trusted to discover new science, it should be able to reproduce what science already knows. Reproduction provides a rigorous checkpoint for an AI scientist: the target claim is…
reinforcement-learning
Bank-World: A Benchmark for Evaluating Agents on Banking Workflows
Bank-World is a benchmark of 50 banking tasks across two simulated institutions. Completing banking work requires more than producing the right calculation: agents must reconcile records, obtain…
reinforcement-learning
Letting AI Formulate the Research Question: Autonomous Research Agents
Systems such as The AI Scientist have shown that AI agents can carry out and write up research, but in those demonstrations humans chose the research area and selected the outputs to show. We study…
machine-learning
Learning to Formulate: Agentic Hardware-Software Co-Design of AI Infrastructure through Progressive Optimization and Verification
AI infrastructure, the chips and software that train and serve AI models, is designed in layers. Layers make the system manageable, but they also fix which choices an optimizer can consider.
math-theory
Information-Driven Collaborative Autonomy for Heterogeneous UAV/UGV Teams
This paper considers coordinating a heterogeneous team of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) traversing a domain containing an unknown number of potentially hazardous…
nlp
Can Image Agents Complete Visual Commissions? A Benchmark and Modular Framework
Visual commissions require image agents to integrate heterogeneous source materials, preserve requirements across dependent stages, and produce coordinated deliverables. Existing evaluations examine…
computer-vision
Clean Sheets and Checkpoints: Evidence Complexity for Certifying Sequential Agent Risk
Dangerous-capability evaluations often test an AI agent from prepared states at ordered milestones. A clean sheet records no successes.
machine-learning
CAPTURER: A Dexterous Aerial Manipulator for Dynamic and Precise Grasping across Diverse Environments
As a representative form of embodied robotic interaction, aerial grasping requires close coordination between the aerial platform and manipulator. Most existing systems perform aerial grasping with…
reinforcement-learning
PCM: A Proof-Carrying Message Protocol for Verifiable Multi-Agent Communication
When one AI agent tells another that "the tests passed" or "a person approved this refund", the receiver has only the sender's word. A2A and MCP authenticate the channel, but the sender is the party…
reinforcement-learning
FilmFlow: Agentic System for 3D Virtual Film Cinematography
Complex camera motion is central to visual storytelling, yet translating cinematographic intent into controllable, executable camera trajectories remains challenging. We introduce FilmFlow, an…
computer-vision
AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics
Agentic robotics systems combine planners with robot harnesses to perform complex manipulation tasks. Recent work improves these systems through better harnesses and external memory, but relies on…
nlp
Planned Restlessness: Delayed Meta Bandits with Budgets
We study episodic finite-horizon Bayesian bandits, or meta-bandits, with independent arms. Each episode draws fresh arm qualities from unknown recurring priors.
computer-vision
Principal-agent hypothesis testing under adaptive experimentation
Principal-agent hypothesis testing studies statistical contracts in which a principal rewards an agent according to data the agent generates. Existing work focuses on the single-shot setting, where…
reinforcement-learning
Simultaneous Gradient Learning in First-Price Auctions
We study equilibrium learning in discretized Bayesian games, focusing on first-price auctions as a testbed for gradient-based learning dynamics under private information. While the symmetric…
reinforcement-learning
SSQA: Sibling-Selective Quadtree Attention for Hierarchical Modeling in Perception Tasks
Perception tasks for navigation in robotics, including aerial platforms such as drones and autonomous driving systems, are inherently structured. Drone-mounted cameras typically capture sky above,…
deep-learning
Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation
Hierarchical language generation separates continuous semantic modeling from discrete text realization, but its effectiveness depends on what the latent space compresses and how the discrete…
nlp
ALPS: Visual State Encoders for World Models
World models turn visual representations into predictions and actions. We argue that their visual foundation should combine physical-state information, native language alignment, and pixel…
deep-learning
From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation
Vision-language-action (VLA) models achieve strong performance across embodied manipulation tasks by unifying visual understanding, language conditioning, and action generation. However, long-horizon…
nlp
Harness Scaling for Generalizable Agentic Reinforcement Learning
Agent harnesses have become a central component of modern agentic systems, shaping how models use tools, manage context, and coordinate long-horizon interaction. Realizing the benefits of these…
nlp