meta-reasoning

Tag

Cards List
#meta-reasoning

Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents

arXiv cs.AI ↗ · 2026-10-05 Cached

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.

0 favorites 0 likes
#meta-reasoning

@dair_ai: Super interesting paper from Meta Superintelligence Labs on controlling long agent runs. They use the same workers and …

X AI KOLs Timeline ↗ · 2026-10-02 Cached

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.

0 favorites 0 likes
#meta-reasoning

Evaluation Awareness Shifts from Format to Context with Model Scale

arXiv cs.CL ↗ · 2026-09-22 Cached

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.

0 favorites 0 likes
#meta-reasoning

When to Plan: Learning to Select Between Reactive Control and Deliberative Planning

arXiv cs.AI ↗ · 2026-07-21 Cached

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.

0 favorites 0 likes
#meta-reasoning

@GitTrend0x: Hermes Meta-Reasoning + Life OS + Self-Improvement Triple Kill Plugins! https://github.com/Cranot/super-hermes… Super Hermes: Teach Hermes to Write Its Own Analytic Prompts + Reflect on Missing Content. Meta-reasoning layer, analyze before…

X AI KOLs Timeline ↗ · 2026-06-30 Cached

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.

0 favorites 0 likes
#meta-reasoning

Finding the Time to Think: Learning Planning Budgets in Real-Time RL

arXiv cs.LG ↗ · 2026-06-26 Cached

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.

0 favorites 0 likes
← Back to home

Submit Feedback