# ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking

arXiv: https://arxiv.org/abs/2510.24698 · HTML: https://mlsanity.com/paper/2510.24698/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

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

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [WebThinker: Empowering Large Reasoning Models with Deep Research Capability](https://mlsanity.com/paper/2504.21776/) (2025)
- [Deep Think with Confidence](https://mlsanity.com/paper/2508.15260/) (2025)
- [Agentic Reinforced Policy Optimization](https://mlsanity.com/paper/2507.19849/) (2025)
- [Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL](https://mlsanity.com/paper/2508.07976/) (2025)
- [BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese](https://mlsanity.com/paper/2504.19314/) (2025)
- [A Survey on Large Language Model Acceleration based on KV Cache Management](https://mlsanity.com/paper/2412.19442/) (2024)
- [LLM Multi-Agent Systems: Challenges and Open Problems](https://mlsanity.com/paper/2402.03578/) (2024)
- [WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent](https://mlsanity.com/paper/2508.05748/) (2025)
- [WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents](https://mlsanity.com/paper/2509.06501/) (2025)
- [TreeRL: LLM Reinforcement Learning with On-Policy Tree Search](https://mlsanity.com/paper/2506.11902/) (2025)
- [TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling](https://mlsanity.com/paper/2508.17445/) (2025)
- [WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning](https://mlsanity.com/paper/2509.13305/) (2025)
- [SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis](https://mlsanity.com/paper/2505.16834/) (2025)
- [DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL](https://mlsanity.com/paper/2509.10446/) (2025)
- [Towards General Agentic Intelligence via Environment Scaling](https://mlsanity.com/paper/2509.13311/) (2025)
- [EvolveSearch: An Iterative Self-Evolving Search Agent](https://mlsanity.com/paper/2505.22501/) (2025)
- [Mind the Confidence Gap: Overconfidence, Calibration, and Distractor Effects in Large Language Models](https://mlsanity.com/paper/2502.11028/) (2025)
- [Scaling Agents via Continual Pre-training](https://mlsanity.com/paper/2509.13310/) (2025)
- [SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation](https://mlsanity.com/paper/2412.13649/) (2024)
- [Pushing Test-Time Scaling Limits of Deep Search with Asymmetric Verification](https://mlsanity.com/paper/2510.06135/) (2025)
- [A Survey on Parallel Reasoning](https://mlsanity.com/paper/2510.12164/) (2025)

## Built on by (most cited first, 14 of 14)

- [Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2604.11753/) (2026)
- [AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents](https://mlsanity.com/paper/2603.27490/) (2026)
- [Nested Browser-Use Learning for Agentic Information Seeking](https://mlsanity.com/paper/2512.23647/) (2025)
- [GISA: A Benchmark for General Information-Seeking Assistant](https://mlsanity.com/paper/2602.08543/) (2026)
- [Argus: Evidence Assembly for Scalable Deep Research Agents](https://mlsanity.com/paper/2605.16217/) (2026)
- [SIGHT: Reinforcement Learning with Self-Evidence and Information-Gain Diverse Branching for Search Agent](https://mlsanity.com/paper/2602.11551/) (2026)
- [Reasoning over mathematical objects: on-policy reward modeling and test time aggregation](https://mlsanity.com/paper/2603.18886/) (2026)
- [AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning](https://mlsanity.com/paper/2605.24486/) (2026)
- [Last Step Matters: Early Uncertainty Cannot Predict Failure in Long-Horizon Agents](https://mlsanity.com/paper/2608.29685/) (2026)
- [On the Overscaling Curse of Parallel Thinking: System Efficacy Contradicts Sample Efficiency](https://mlsanity.com/paper/2601.21619/) (2026)
- [FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search](https://mlsanity.com/paper/2606.00660/) (2026)
- [Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking](https://mlsanity.com/paper/2606.07689/) (2026)
- [Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows](https://mlsanity.com/paper/2606.14672/) (2026)
- [Beyond Confidence: Test-Time Scaling for Multi-Turn Search Agents via Retrieval Grounding](https://mlsanity.com/paper/2608.24024/) (2026)

## Abstract (arXiv)

Parallel thinking expands exploration breadth, complementing the deep exploration of information-seeking (IS) agents to further enhance problem-solving capability. However, conventional parallel thinking faces two key challenges in this setting: inefficiency from repeatedly rolling out from scratch, and difficulty in integrating long-horizon reasoning trajectories during answer generation, as limited context capacity prevents full consideration of the reasoning process. To address these issues, we propose ParallelMuse, a two-stage paradigm designed for deep IS agents. The first stage, Functionality-Specified Partial Rollout, partitions generated sequences into functional regions and performs uncertainty-guided path reuse and branching to enhance exploration efficiency. The second stage, Compressed Reasoning Aggregation, exploits reasoning redundancy to losslessly compress information relevant to answer derivation and synthesize a coherent final answer. Experiments across multiple open-source agents and benchmarks demonstrate up to 62% performance improvement with a 10--30% reduction in exploratory token consumption.