# Scaling Test-time Compute for LLM Agents

arXiv: https://arxiv.org/abs/2506.12928 · HTML: https://mlsanity.com/paper/2506.12928/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 15 Jun 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 25 of 25)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [ToolRL: Reward is All Tool Learning Needs](https://mlsanity.com/paper/2504.13958/) (2025)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models](https://mlsanity.com/paper/2408.00724/) (2024)
- [Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks](https://mlsanity.com/paper/2411.04468/) (2024)
- [OS-Copilot: Towards Generalist Computer Agents with Self-Improvement](https://mlsanity.com/paper/2402.07456/) (2024)
- [RM-R1: Reward Modeling as Reasoning](https://mlsanity.com/paper/2505.02387/) (2025)
- [Tree Search for Language Model Agents](https://mlsanity.com/paper/2407.01476/) (2024)
- [Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling](https://mlsanity.com/paper/2502.06703/) (2025)
- [Agents: An Open-source Framework for Autonomous Language Agents](https://mlsanity.com/paper/2309.07870/) (2023)
- [Symbolic Learning Enables Self-Evolving Agents](https://mlsanity.com/paper/2406.18532/) (2024)
- [RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text](https://mlsanity.com/paper/2305.13304/) (2023)
- [Self-rewarding correction for mathematical reasoning](https://mlsanity.com/paper/2502.19613/) (2025)
- [A Comparative Study on Reasoning Patterns of OpenAI's o1 Model](https://mlsanity.com/paper/2410.13639/) (2024)
- [AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents](https://mlsanity.com/paper/2502.05957/) (2025)
- [VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks](https://mlsanity.com/paper/2401.13649/) (2024)
- [Sample, Don't Search: Rethinking Test-Time Alignment for Language Models](https://mlsanity.com/paper/2504.03790/) (2025)
- [Bag of Tricks for Inference-time Computation of LLM Reasoning](https://mlsanity.com/paper/2502.07191/) (2025)
- [TapeAgents: a Holistic Framework for Agent Development and Optimization](https://mlsanity.com/paper/2412.08445/) (2024)

## Built on by (most cited first, 30 of 63)

- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL](https://mlsanity.com/paper/2508.13167/) (2025)
- [AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2509.08755/) (2025)
- [Budget-Aware Tool Use Enables Effective Agent Scaling](https://mlsanity.com/paper/2511.17006/) (2025)
- [Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training](https://mlsanity.com/paper/2508.00414/) (2025)
- [Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments](https://mlsanity.com/paper/2602.01244/) (2026)
- [Efficient Agents: Building Effective Agents While Reducing Cost](https://mlsanity.com/paper/2508.02694/) (2025)
- [Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution](https://mlsanity.com/paper/2509.25301/) (2025)
- [Benchmark Test-Time Scaling of General LLM Agents](https://mlsanity.com/paper/2602.18998/) (2026)
- [Agentic Rubrics as Contextual Verifiers for SWE Agents](https://mlsanity.com/paper/2601.04171/) (2026)
- [Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification](https://mlsanity.com/paper/2601.15808/) (2026)
- [Structured Scaling of AI Discovery Across Diverse Scientific Domains](https://mlsanity.com/paper/2604.19341/) (2026)
- [Towards Personalized Deep Research: Benchmarks and Evaluations](https://mlsanity.com/paper/2509.25106/) (2025)
- [Scaling Test-Time Compute for Agentic Coding](https://mlsanity.com/paper/2604.16529/) (2026)
- [A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression](https://mlsanity.com/paper/2604.19572/) (2026)
- [SSRL: Self-Search Reinforcement Learning](https://mlsanity.com/paper/2508.10874/) (2025)
- [Scaling Agents for Computer Use](https://mlsanity.com/paper/2510.02250/) (2025)
- [When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation](https://mlsanity.com/paper/2604.00892/) (2026)
- [Inference-Time Budget Control for LLM Search Agents](https://mlsanity.com/paper/2605.05701/) (2026)
- [Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents](https://mlsanity.com/paper/2602.02995/) (2026)
- [How Far Are We from Genuinely Useful Deep Research Agents?](https://mlsanity.com/paper/2512.01948/) (2025)
- [Spend Less, Reason Better: Budget-Aware Value Tree Search for LLM Agents](https://mlsanity.com/paper/2603.12634/) (2026)
- [The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck](https://mlsanity.com/paper/2605.11039/) (2026)
- [Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization](https://mlsanity.com/paper/2601.05432/) (2026)
- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents](https://mlsanity.com/paper/2605.06908/) (2026)
- [Learning to Ideate for Machine Learning Engineering Agents](https://mlsanity.com/paper/2601.17596/) (2026)
- [TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents](https://mlsanity.com/paper/2602.11767/) (2026)
- [Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds](https://mlsanity.com/paper/2608.02636/) (2026)
- [StyleBench: Evaluating thinking styles in Large Language Models](https://mlsanity.com/paper/2509.20868/) (2025)

## Abstract (arXiv)

Scaling test time compute has shown remarkable success in improving the reasoning abilities of large language models (LLMs). In this work, we conduct the first systematic exploration of applying test-time scaling methods to language agents and investigate the extent to which it improves their effectiveness. Specifically, we explore different test-time scaling strategies, including: (1) parallel sampling algorithms; (2) sequential revision strategies; (3) verifiers and merging methods; (4)strategies for diversifying rollouts.We carefully analyze and ablate the impact of different design strategies on applying test-time scaling on language agents, and have follow findings: 1. Scaling test time compute could improve the performance of agents. 2. Knowing when to reflect is important for agents. 3. Among different verification and result merging approaches, the list-wise method performs best. 4. Increasing diversified rollouts exerts a positive effect on the agent's task performance.