Tag
The paper introduces MIRA, a hierarchical meta-reasoning architecture for long-horizon research agents that separates research allocation from execution, and MIRA-AC, a generative actor-critic that learns credit assignment at meta-reasoning decision boundaries, improving theorem proving and neural architecture research.
Meta Superintelligence Labs introduces agentic meta-reasoning, an inference-time harness where a controller decides what work to run next in long agent runs, boosting ProgramBench from 63.7% to 71.5% with GPT-5.5 under the same workers and budget. Gains of 3.6-4.2 points hold across ProofBench, ARC-AGI-2 and LongCoT-mini when averaged over frontier models.
The paper investigates evaluation awareness in compact language models, revealing that smaller models rely on format sensitivity while larger models use context reasoning, and proposes a dual-pathway intervention to suppress evaluation awareness.
This paper introduces a reinforcement learning method for training a meta-reasoning policy that selects between fast reactive control and slower deliberative planning based on uncertainty in the reactive policy, achieving better balance and adaptivity in navigation tasks.
A series of open-source plugins for the Hermes AI agent, including Meta-Reasoning (Super Hermes), Life OS, Self-Improvement Dojo, Skill Marketplace, and Spotify Control Plugin. These plugins deeply integrate with the Hermes core loop, driving the agent's daily life integration, self-evolution, and automated marketplace development.
This paper introduces variable-delay real-time RL, where agents decide how long to deliberate in environments that progress during decision-making, and proposes a lightweight gating policy to select state-dependent planning budgets, outperforming fixed-budget and heuristic baselines in several real-time games.