MLINFO COLLECTION
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。
Lattice-type modular reconfigurable robots rearrange standardized modules across tasks. Dedicated transport robots reduce module weight and cost by eliminating module level reconfiguration actuators.
Trajectory-level GRPO is a common approach for training multi-step GUI agents, but repeatedly rolling out complete trajectories from the task root can be inefficient: task-level rewards provide…
Financial AI systems must support decision-bearing questions involving payments, collections, cash flow, and compliance while ensuring numerical accuracy, traceability, and auditability. Large…
LLM-based agents are increasingly used to complete complex, long-horizon tasks without human intervention. To make progress toward the task goal, agents need to perform different duties, such as…
Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Prompt injection turns this excess access into an opportunity to redirect execution…
Large language model agents have begun to carry out laboratory measurements, but their scientific conclusions are useful only if they hold up under scrutiny. Demonstrating this requires controlled…
PhysicsNeMo-Mesh is the mesh module of the open-source PhysicsNeMo library. It provides mesh processing similar to PyVista, but on the GPU, in batches, and inside PyTorch's automatic differentiation.
Many high-stakes collective problems, e.g., climate mitigation and pandemic response, share a structure in which risk materializes unless a group threshold is met. This threshold is often uncertain,…
Reproducing a published 3DGS paper takes weeks of expert engineering before any extension can be proposed. Prior autonomous-research systems read papers, draft hypotheses, and write code, but are…
SNNs are attracting interest due to their potential for energy efficiency and event-driven processing. However, neuromorphic hardware is not yet mature enough to enable embedded deployment of complex…
Public charging of electric vehicles (EVs) adds a large and synchronized load to the distribution feeders. In most networks, it is rare to overload a feeder at the same time.
Balatro, a 2024 roguelike deckbuilder, presents three difficulties that have historically derailed reinforcement learning methods: a 3,000-action state-dependent action space, horizons of several…
Sparse-view computed tomography (CT) reduces the number of acquired projections, but conventional sampling strategies are designed primarily for image reconstruction rather than for downstream…
World models let observers explore and interact with generated worlds. Recent work shows that when observers revisit a region, current models often fail to regenerate it consistently.
Large language models pass most functional-correctness benchmarks, but passing tests says little about whether their code is readable, efficient or secure. Many techniques claim to improve these…
Fine-grained audio-visual question answering (AVQA) requires models to resolve complex cross-modal correspondences and temporally grounding from sparsely distributed evidence. Omni-modal agents,…
Training-time multi-agent system (MAS) design seeks to learn reusable orchestration policies, yet prevailing approaches remain largely one-shot: an Orchestrator generates a system but only observes…
Organisations keep decades of financial records as scanned PDFs on shared drives, and AI agents can now reach those drives through Model Context Protocol (MCP) servers. Existing benchmarks do not…
Predictive world-model objectives need not organize latent histories according to distinctions required for later control. With privileged simulator access during training, should response-derived…
Multi-agent debate systems require agents to retain and revisit arguments across multiple rounds, yet limited context windows and unstructured memories make relevant information increasingly…
Embodied instruction following in interactive environments requires agents to interpret natural language commands and complete long-horizon tasks. Existing planners either rely on large labeled…
Autonomous navigation in off-road terrain is commonly achieved using hierarchical control and planning architectures that rely on explicit cost maps and one-way information flow from a high-level…
Verifying numerical claims in research written by AI agents is an important but challenging problem. Recent benchmarks show that many agent-written papers fail integrity checks, but such verdicts,…
When an LLM agent fails, repair methods choose which action to replace and what to put in its place. They often score candidate repairs with greedy replay, a stronger model, an environment oracle, or…