Can a Cloud-Native Harness Make Agents Reliable Beyond the Desktop?
Kubernetes co-creators Craig McLuckie and Joe Beda aim to bring agent harnesses fully into the cloud.
INTELLIGENCE & DISCOVERY
最新动态AI 前沿
更多更新
机构原始发布Emotional optimization by newsroom AI needs behavioural evaluation
Nature Machine Intelligence, Published online: 07 October 2026; doi:10.1038/s42256-026-01315-8 When newsroom artificial intelligence (AI) engages in emotional packaging, it changes how a story feels, shaping whether people approach, trust…
Toward Part-Aware Choral Transcription with singing voice assignment
Single-instrument automatic music transcription (AMT) has advanced substantially, yet choral applications require soprano, alto, tenor, and bass (SATB) to be transcribed as separate parts. Recent note-level choral AMT instead produces a si…
Factorization-Guided Training and Inference for Diffusion-Drafted Speculative Decoding
Speculative decoding accelerates large language model inference through parallel verification of tokens proposed by a drafter. Diffusion drafters further parallelize proposal generation, but greater proposal capacity or higher mean accepte…
Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models
Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by leveraging rich representations from pretrained vision-language models. However, their deployment in real-world environments remains limited by…
LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets
Evaluating agents by outcomes alone can obscure the capabilities that produce them. This problem is especially pronounced in evolving environments, where outcomes reflect a closed-loop interaction between agent behavior and changing extern…
Characterizing the role of reasoning tokens in large language models as state over tokens
Nature Machine Intelligence, Published online: 07 October 2026; doi:10.1038/s42256-026-01303-y When large language models ‘reason’ about a problem, they might still solve it differently from what their reasoning transcript suggest. In this…
Supercomputing researchers document evolution of AI hardware
An ongoing survey tracks the latest AI accelerator systems to keep hardware relevant for Lincoln Laboratory staff and sponsors.
Chris Bourg named vice provost and Barbara K. Ostrom (1978) Director of the MIT Libraries
As director, Bourg has focused on digital access, open and equitable scholarly publishing, and expanded support for data-intensive research.
MIT announces the MIT for America initiative, to strengthen STEM education across the country
The effort aims to help U.S. learners from kindergarten to community college, with an emphasis on math, making, and the constructive use of AI.
FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents
Repository-level software engineering (SWE) is a challenging long-horizon setting: agents must reason over extended interactions, use tools, and adapt to stateful environments. Recent work trains SWE agents with reinforcement learning meth…
Consistent Distribution Matching for Data-Free Diffusion Distillation
Flow and diffusion models suffer from slow inference due to computationally expensive numerical integration. Distillation provides a promising way for a student model to learn from a teacher's dynamics, enabling one-step or few-step genera…
Import AI 475: Swarm scaling; Google DeepMind watermarks biology; and the AI science economy
Who chooses what AI gets to do?
HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention
Large language model (LLM) agents are increasingly capable of acting in complex tool-use environments, yet they often fail to recognize when tasks are infeasible and no valid solution exists. Recent work has formalized this reliability gap…
MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents
Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent memory systems construct memory in a query-agnostic manner, which can incur unnecessary pre…
BRACE: Adapting Whole-Body References for Force and Terrain Aware Humanoid Motion Tracking
Whole-body tracking has become the interface through which operators drive humanoid robots, yet the references it consumes are recorded on level ground and carrying nothing, so the tracker is aware of neither the forces the robot must exch…