10 results on this page
KnowSim is an evaluation framework that simulates users with explicit, evolving knowledge states to assess whether LLM assistants adapt information delivery to user understanding. Across 705 human-AI sessions and evaluations of nine LLMs, its metrics aligned with human judgments and showed that the strongest model varies by user knowledge level.
KernelArc is a multi-agent framework for autonomous GPU kernel optimization across heterogeneous workloads. On NVIDIA H100 and B200 GPUs, its implementations ranked first on representative L1, L2, Quantization, and FlashInfer tasks in the July 30, 2026 SOL-ExecBench snapshot.
AWS outlines enterprise patterns for operating many agentic AI systems across diverse frameworks, models, and providers. The guidance focuses on preserving flexibility and enabling multi-agent systems to scale together without vendor lock-in.
The paper proposes Transition Complexity Profile (TCP), a reproducible framework for measuring how difficult game-world transition prediction is at a specified interface. It evaluates branching, interaction-driven uncertainty, opponent influence, and temporal or spatial dependencies to improve comparisons across game-modeling and reinforcement-learning benchmarks.
Tactile robotics is expanding from sensor hardware into datasets, foundation models, and evaluation benchmarks. Research shows touch improves physical reasoning and robot success, but inconsistent sensor formats create major cross-device transfer challenges.
AWS Professional Services uses a multi-agent framework on Amazon Bedrock AgentCore to automate enterprise cloud migrations end to end. Specialized agents cover discovery, infrastructure-as-code generation, portfolio governance, and post-migration operations, reducing IaC development time from weeks to minutes.
OpenAI’s Private Safety Processing is designed to detect abuse across multiple interactions without requiring customers to hand over their data. The approach preserves Zero Data Retention and contrasts with Anthropic’s stated 30-day retention requirement.
FinSkillBench is a new benchmark for testing AI agents on portfolio construction, risk management, and fundamental analysis. Across nine models, curated procedural skills raised mean performance from 0.366 to 0.528, while self-generated skills delivered little benefit.
Xiaomi stabilized in Q2 2026 while expanding its AI strategy across models, chips, and robotics. Its MiMo-V2.5 model led OpenRouter call charts, the Xuanjie chip passed mass verification, and a humanoid robot began factory operations with a reported 98% success rate.
Marvell and Google are deepening their partnership on custom AI chip development. Marvell is giving Google the right to purchase up to $12.2 billion in Marvell stock, strengthening their long-term alignment in the AI hardware race.