Arbor: Tree Search as a Cognition Layer for Autonomous Agents

• URL: http://arxiv.org/abs/2606.12563v1
• Date: Wed, 10 Jun 2026 18:14:56 GMT
• Title: Arbor: Tree Search as a Cognition Layer for Autonomous Agents
• Abstract summary: Arbor is a multi-agent framework that introduces structured tree search as a cognition layer for autonomous agents.<n>Arbor generalizes to multiple generations of hardware platform, and run-to-run variance is within 2 percentage points demonstrating that the method is hardware-agnostic and reproducible.
• Score: 11.049500825171245
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Arbor is a multi-agent framework that introduces structured tree search as a cognition layer for autonomous agents operating in large, stateful action spaces. Prior autonomous optimization systems operate on isolated targets with stateless evaluation. Arbor instead maintains an explicit search tree of scored hypotheses that serves as the shared working memory across agents, evolving with every measurement, treating failures as diagnostic signal that reshapes subsequent exploration, and expanding as prior successes shift the bottleneck distribution. We validate Arbor on full-stack LLM inference optimization, a domain where achieving peak performance has historically required coordinated effort from engineering teams across the application, framework, compiler, kernel, and hardware stack. Arbor pairs an Orchestrator agent, which drives optimization by delegating to Domain Specialists across the inference stack, with a Critic agent that safeguards stability through root-cause analysis, introspection, and measurement validation -- a checks-and-balances architecture where neither agent can unilaterally drive the system. Agent capabilities are decomposed into hard skills (domain expertise) and soft skills (coordination protocols that determine how contributions compose), enabling fully autonomous multi-day campaigns. Arbor achieves up to 193% inference throughput-latency Pareto improvement over vendor-optimized baselines, while a single agent without the harness plateaus at +33% throughput improvement and crashes irrecoverably within hours. Arbor generalizes to multiple generations of hardware platform, and run-to-run variance is within 2 percentage points demonstrating that the method is hardware-agnostic and reproducible.

Related papers

• AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities [55.23913617185508]
  Agent is an open-source, lightweight, and infrastructure for evaluating Large Language Models (LLMs)-based agents.<n>It organizes the evaluation process around three independent components, namely Benchmark, Harness and Environment.<n>It features a fault-tolerant runtime and comprehensive trajectory analysis tools to transparently diagnose failure modes like reward-hacking.
  arXiv  Detail & Related papers  (2026-07-15T11:11:17Z)
• Toward Generalist Autonomous Research via Hypothesis-Tree Refinement [150.99641031769633]
  We introduce Arbor, a framework for autonomous research that combines a long-lived coordinator, short-lived executors, and Hypothesis Tree Refinement (HTR)<n>As results return, Arbor updates the tree, propagates reusable lessons, refines the search frontier, and admits verified improvements.
  arXiv  Detail & Related papers  (2026-06-10T10:57:05Z)
• The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development? [80.24951682268332]
  We introduce the Meta-Agent Challenge (MAC), an evaluation framework designed to test the capacity of frontier models for autonomous agent development.<n>To ensure evaluation integrity, this framework is secured by multi-layer defenses against reward hacking.<n>We demonstrate that meta-agents rarely match human-engineered baseline policies, and the few that do are dominated by proprietary frontier models.
  arXiv  Detail & Related papers  (2026-06-03T04:58:17Z)
• InferenceBench: A Benchmark for Open-Ended LLM Inference Optimization by AI Agents [15.892896819368751]
  We introduce InferenceBench, where an agent must deploy an OpenAI-compatible inference server and optimize the speed of LLM inference.<n>Three optimization scenarios isolate distinct bottlenecks of inference.<n>Agents reliably improve over a naive PyTorch baseline.<n>Overall, InferenceBench reflects the ability of agents to operate in an open-ended AI engineering setting.
  arXiv  Detail & Related papers  (2026-05-20T15:55:21Z)
• AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation [59.964989458924585]
  AdaExplore is an agent framework that enables self-improvement via accumulated execution feedback for performance-critical kernel code generation.<n>In the adaptation stage, the agent synthesizes tasks and converts recurring failures into a reusable memory of validity rules.<n>In the search stage, the agent organizes candidate kernels as a tree and alternates between small local refinements and larger structural regeneration.
  arXiv  Detail & Related papers  (2026-04-17T18:25:03Z)
• TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAG [71.06073770344732]
  Agentic retrieval-augmented generation (RAG) formulates question answering as a multi-step interaction between reasoning and information retrieval.<n>We present TreePS-RAG, an online, tree-based RL framework for agentic RAG that enables step-wise credit assignment while retaining outcome-only rewards.
  arXiv  Detail & Related papers  (2026-01-11T14:07:30Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• ArchPilot: A Proxy-Guided Multi-Agent Approach for Machine Learning Engineering [18.83090180326138]
  ArchPilot is a multi-agent system that integrates architecture generation, proxy-based evaluation, and adaptive search into a unified framework.<n>It prioritizes high-potential candidates with minimal reliance on expensive full training runs, facilitating efficient ML engineering under limited budgets.
  arXiv  Detail & Related papers  (2025-11-06T02:14:59Z)
• Alita-G: Self-Evolving Generative Agent for Agent Generation [54.49365835457433]
  We present ALITA-G, a framework that transforms a general-purpose agent into a domain expert.<n>In this framework, a generalist agent executes a curated suite of target-domain tasks.<n>It attains strong gains while reducing computation costs.
  arXiv  Detail & Related papers  (2025-10-27T17:59:14Z)
• Tree Search for LLM Agent Reinforcement Learning [23.7084695563981]
  Tree-based Group Relative Policy Optimization (Tree-GRPO) is a grouped agent RL method based on tree search.<n>By sharing common prefixes, the tree search sampling increases the number of rollouts achievable.<n>We demonstrate that the objective of intra-tree level group relative policy optimization is equivalent to that of step-level direct preference learning.
  arXiv  Detail & Related papers  (2025-09-25T14:37:09Z)
• xOffense: An AI-driven autonomous penetration testing framework with offensive knowledge-enhanced LLMs and multi agent systems [0.402058998065435]
  xOffense is an AI-driven, multi-agent penetration testing framework.<n>It shifts the process from labor-intensive, expert-driven manual efforts to fully automated, machine-executable scaling seamlessly with computational infrastructure.
  arXiv  Detail & Related papers  (2025-09-16T12:45:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.