# Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

arXiv: https://arxiv.org/abs/2606.11926 · HTML: https://mlsanity.com/paper/2606.11926/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 59 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 30 of 50)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models](https://mlsanity.com/paper/2310.04406/) (2023)
- [MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering](https://mlsanity.com/paper/2410.07095/) (2024)
- [AFlow: Automating Agentic Workflow Generation](https://mlsanity.com/paper/2410.10762/) (2024)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://mlsanity.com/paper/2505.22954/) (2025)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [Memory in the Age of AI Agents](https://mlsanity.com/paper/2512.13564/) (2025)
- [ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery](https://mlsanity.com/paper/2410.05080/) (2024)
- [AIDE: AI-Driven Exploration in the Space of Code](https://mlsanity.com/paper/2502.13138/) (2025)
- [RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts](https://mlsanity.com/paper/2411.15114/) (2024)
- [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://mlsanity.com/paper/2604.25850/) (2026)
- [A Comprehensive Survey on Long Context Language Modeling](https://mlsanity.com/paper/2503.17407/) (2025)
- [AutoHarness: improving LLM agents by automatically synthesizing a code harness](https://mlsanity.com/paper/2603.03329/) (2026)
- [AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench](https://mlsanity.com/paper/2507.02554/) (2025)
- [The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs](https://mlsanity.com/paper/2509.09677/) (2025)

## Built on by (most cited first, 22 of 22)

- [AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement](https://mlsanity.com/paper/2608.20318/) (2026)
- [Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering](https://mlsanity.com/paper/2607.28568/) (2026)
- [ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond](https://mlsanity.com/paper/2608.14354/) (2026)
- [Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents](https://mlsanity.com/paper/2607.09195/) (2026)
- [Towards Autonomous and Auditable Medical Imaging Model Development](https://mlsanity.com/paper/2607.10522/) (2026)
- [What is Missing from AI Post-Training AI: An Empirical Analysis](https://mlsanity.com/paper/2608.19072/) (2026)
- [Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks](https://mlsanity.com/paper/2608.05144/) (2026)
- [ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs](https://mlsanity.com/paper/2608.12788/) (2026)
- [AIM: Agentic Idea Management for Automated Research](https://mlsanity.com/paper/2609.38445/) (2026)
- [Mathematical Discovery in the Wild: AI-Guided Proofs in Banach Space Theory](https://mlsanity.com/paper/2607.17388/) (2026)
- [Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents](https://mlsanity.com/paper/2610.02525/) (2026)
- [IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation](https://mlsanity.com/paper/2610.04074/) (2026)
- [EvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolution](https://mlsanity.com/paper/2610.04517/) (2026)
- [MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-Training](https://mlsanity.com/paper/2610.05398/) (2026)
- [When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation](https://mlsanity.com/paper/2610.12061/) (2026)
- [EvoBelief: Falsifiable World Models for Self-Improving LLM Agents](https://mlsanity.com/paper/2610.12789/) (2026)
- [JANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models](https://mlsanity.com/paper/2610.13194/) (2026)
- [AgentSWE: Can Coding Agents Build the Agent You Actually Want?](https://mlsanity.com/paper/2610.13361/) (2026)
- [SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces](https://mlsanity.com/paper/2610.18025/) (2026)
- [Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents](https://mlsanity.com/paper/2610.18082/) (2026)
- [AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement](https://mlsanity.com/paper/2610.18083/) (2026)
- [SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm](https://mlsanity.com/paper/2610.20431/) (2026)

## Abstract (arXiv)

Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the evidence, and carry the resulting lessons into later attempts. We study how an AI agent can run this loop autonomously over long horizons. We introduce Arbor, a general framework for autonomous research that combines a long-lived coordinator, short-lived executors, and Hypothesis Tree Refinement (HTR), a persistent tree that links hypotheses, artifacts, evidence, and distilled insights across time. The coordinator manages global research strategy over the tree, while executors implement and test individual hypotheses in isolated worktrees. As results return, Arbor updates the tree, propagates reusable lessons, refines the search frontier, and admits verified improvements. This design turns autonomous research from a sequence of local attempts into a cumulative process in which strategy, execution, and evidence are carried across time. We evaluate Arbor under Autonomous Optimization (AO), an operational setting where an agent improves an initial research artifact through iterative experimentation without step-level human supervision. Across six real research tasks in model training, harness engineering, and data synthesis, Arbor achieves the best held-out result on all six tasks, attaining more than 2.5x the average relative held-out gain of Codex and Claude Code under the same task interface and resource budget. On MLE-Bench Lite, Arbor reaches 86.36% Any Medal with GPT-5.5, the strongest result in our comparison.