Termsslug: test-time-compute

Test-Time Compute

测试时计算

Strategy increasing computational resources during inference to improve output quality.

Curated Intelligence

6 items · Page 1/1
机器之心 (微信公众号)T2·Agents
85 pts
Tsinghua Proposes ParallelWorld: Multi-Step Simulation Boosts Embodied Agent Success to 83%

Researchers from Tsinghua University and NUS introduced ParallelWorld, integrating test-time computation into high-level planning for embodied agents. By simulating multiple candidate action paths and comparing future observations, the method allows robots to anticipate consequences before execution, boosting task success rates from 56% to 83% and offering a new paradigm for embodied decision optimization.

Latent SpaceT1·Agents
68 pts
Anthropic Unveils Dynamic Workflows for Claude Multi-Agent Orchestration and Test-Time Compute Optimization

Anthropic officially introduced 'Dynamic Workflows' (Flows) at AI Engineer NYC, a new multi-agent orchestration feature designed to coordinate Claude Managed Agents for complex workloads. The system optimizes test-time compute allocation to accelerate capability emergence on hard problems, aiming to make scientific discovery broadly accessible via API.

OpenAI 官方博客T1·Models
85 pts
OpenAI Releases GPT-5.5 System Card: Enhanced Safety and Autonomy

OpenAI released the GPT-5.5 system card, detailing a model designed for complex real-world tasks with enhanced tool use, self-verification, and autonomous execution capabilities. The document discloses red-teaming results for cybersecurity and biology, emphasizing the deployment of the strictest safety safeguards to date. GPT-5.5 Pro, sharing the same underlying model but using parallel test-time compute, underwent separate evaluation for specific risk scenarios.

Hugging Face BlogT1·Models
78 pts
Kimina-Prover Introduces Test-time RL Search for Formal Reasoning

The Project Numina team released Kimina-Prover, applying test-time reinforcement learning (RL) search to large formal reasoning models. This approach aims to significantly enhance accuracy in mathematical theorem proving and complex logical deduction by dynamically optimizing inference paths, marking a new advancement in AI symbolic reasoning.