mlsanityData to 7 Oct 2026

Curriculum Guided Massive Multi Agent System Solving For Robust Long Horizon Tasks

arXiv 2512.08545 ↗First posted 9 Dec 2025cs.CL cs.AI cs.CVcited by 1

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Large Language Models and multi-agent systems have shown promise in decomposing complex tasks, yet they struggle with long-horizon reasoning tasks and escalating computation cost. This work introduces a hierarchical multi-agent architecture that distributes reasoning across a 64*64 grid of lightweight agents, supported by a selective oracle. A spatial curriculum progressively expands the operational region of the grid, ensuring that agents master easier central tasks before tackling harder peripheral ones. To improve reliability, the system integrates Negative Log-Likelihood as a measure of confidence, allowing the curriculum to prioritize regions where agents are both accurate and well calibrated. A Thompson Sampling curriculum manager adaptively chooses training zones based on competence and NLL-driven reward signals. We evaluate the approach on a spatially grounded Tower of Hanoi benchmark, which mirrors the long-horizon structure of many robotic manipulation and planning tasks. Results demonstrate improved stability, reduced oracle usage, and stronger long-range reasoning from distributed agent cooperation.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 4 of its 8 references that are in the map. First posted on arXiv 9 Dec 2025.

Builds on

4 of 8 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Position: Scaling LLM Agents Requires Asymptotic Analysis with LLM Primitives4 Feb

Other references · 3

  1. 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 515
  2. 2023Faith and Fate: Limits of Transformers on Compositionalitycited by 496
  3. 2025Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Automatic Hard Example Synthesis with Multi-Level Agentic Data Curationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Closed-Loop Multi-Agent Framework for Robust Multi-Robot Manipulation
  2. 2026Planner Matters! An Efficient and Unbalanced Multi-agent Collaboration Framework for Long-horizon Planning
  3. 2024MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation
  4. 2025Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning
  5. 2026Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning
  6. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
  7. 2024LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments
  8. 2026AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning