---
title: 'FlowSearch: Autonomous Research Workflow'
url: https://www.emergentmind.com/topics/flowsearch
type: topic
---

# FlowSearch: Autonomous Research Workflow

FlowSearch is a multi-agent research framework that operationalizes deep research workflows via a dynamically evolving, structured knowledge flow graph. The system integrates large language model (LLM) agents to plan, execute, and refine decomposed research tasks, supporting parallel exploration, real-time reasoning, and iterative adjustment. FlowSearch attains state-of-the-art results across a spectrum of reasoning and scientific benchmarks, offering concrete advances in autonomous scientific discovery and complex information synthesis [2510.08521].

## 1. System Architecture and Components

FlowSearch is architected around a dynamic, directed acyclic graph (DAG) formalization of knowledge flow, enabling decentralized, modularized execution and hierarchical decomposition of research queries. The core system comprises three principal LLM-powered components and a summarizer:

- **Knowledge Flow Planner**: Initializes and recursively expands the knowledge flow DAG \(G=(V,E)\), where nodes encode subtasks—distinguished as `search`, `solve`, or `answer`—and edges model logical dependencies. The InternPlanner LLM is fine-tuned to generate graph expansions \(f^{expand}_\theta(\cdot)\), iterating until decomposition is complete.

- **Knowledge Collector**: Identifies “ready” nodes—those with all predecessors in a solved state—and dispatches them in parallel to LLM-driven executors with tool augmentation (web search, OCR, code execution). For node \(v_i=(t_i, d_i, s_i, c_i)\), execution semantics are:
  \[
  (s_i, c_i)\;=\;f^{exec}(t_i, d_i\mid \{\,c_j\mid (v_j\!\to\!v_i)\in E\})
  \]
  with \(s_i \in \{\text{Success, Failure}\}\) and \(c_i\) a distilled knowledge summary.

- **Knowledge Flow Refiner**: Following each execution cycle, this agent updates the DAG via graph-edit operations: \(\{AddNode, DelNode, ModNode, AddEdge, DelEdge, ModEdge\}\) as specified by the response of a refinement LLM \(f^{refine}(\cdot)\), pruning dead ends and integrating new insights.

- **Summarizer / Conclusion Generator**: Upon resolution of all dependencies for the query node, generates either a concise answer or a comprehensive scientific report, conditioning on direct predecessors (QA mode) or the full graph (report mode).

The system executes the following loop until task completion: Planner expansion, parallel Collector execution, DAG refinement, and finally, summarization.

## 2. Formalization of the Dynamic Knowledge Flow

FlowSearch models the evolving research plan as a DAG \(G=(V,E)\):

- **Nodes**: Each node \(v_i\) is a tuple:
  \[
  v_i = (t_i,\, d_i,\, s_i,\, c_i)
  \]
  with \(t_i\) denoting the task type (`search`, `solve`, `answer`), \(d_i\) a natural-language subtask description, \(s_i \in \{\text{Pending, Success, Failure}\}\), and \(c_i\) the content summary upon successful execution.

- **Edges**: \(e_{ij} = (v_i \to v_j, r_{ij})\), encoding dependency relations \(r_{ij}\) from a pre-defined set.

- **Expansion**:
  \[
  G_{t+1}^{init} = f^{expand}_\theta(G_t^{init}), \quad G_0^{init} = (\{v_{query}\}, \emptyset)
  \]
  Each expansion appends new nodes \(V_{add}\) and edges \(E_{add}\).

- **Execution**:
  \[
  (s_i, c_i) = f^{exec}\Bigl(t_i, d_i \mid \{c_j \mid (v_j \to v_i) \in E_t\}\Bigr)
  \]

- **Refinement**:
  \[
  G_{t+1} = f^{refine}(V_t, E_t)
  \]
  with \(f^{refine}\) outputting a sequence of edit operations as above.

## 3. Algorithmic Structure

Three key algorithmic procedures govern FlowSearch’s operation:

- **INITIAL_PLAN**: Recursively expands the initial query node until no further subtasks are proposed, producing the base DAG structure.
  ```python
  procedure INITIAL_PLAN(q):
      G ← ({v_query=(answer,q,Pending,∅)}, ∅)
      repeat:
          Δ ← f_expand(G)
          if Δ is empty: break
          G.V ← G.V ∪ Δ.V_add
          G.E ← G.E ∪ Δ.E_add
      until no more expansion
      return G
  ```

- **PARALLEL_EXPAND**: For each decomposable, pending node, proposes further subtask expansions in parallel, supporting late-arising task branching.

- **EXECUTE_AND_REFINE**: Executes all ready, dependency-satisfied leaf nodes in parallel; subsequently refines the DAG as new insights or failures are surfaced.
  ```python
  procedure EXECUTE_AND_REFINE(G):
      while query_node s != Success:
          ready ← {v | preds(v) all have s=Success and v.s=Pending}
          parallel for v in ready:
              (v.s, v.c) ← f_exec(v.t, v.d | {c_j| j→i ∈ G.E})
          ops ← f_refine(G)
          G ← APPLY_OPS(G, ops)
      return G
  ```
  
A node evaluation scoring function (e.g., \(\text{score}(v_i) = \alpha \cdot \text{depth}(v_i) - \beta \cdot \text{uncertainty}(c_i)\)) may guide refinement decisions, such as node splitting or pruning.

## 4. Empirical Evaluation and Benchmark Results

FlowSearch was evaluated on four challenging benchmarks:

- **GAIA**: 165 multimodal, tool-oriented items at 3 difficulty levels.
- **GPQA-diamond**: 198 expert-authored multiple-choice items in biology, chemistry, and physics.
- **HLE**: 2,500 multimodal questions spanning STEM and humanities.
- **TRQA-lit**: 172 biomedical target-discovery questions.

Performance metrics are primarily accuracy (%) per domain or difficulty level. FlowSearch demonstrates the following results (excerpted):

| Method                | GAIA Avg | GPQA Avg | HLE (All) | TRQA  |
|-----------------------|----------|----------|-----------|-------|
| GPT-5                 |    —     | 85.35    | 24.76     | 49.4  |
| OpenAI DR             |  67.36   | —        | 26.60     | 60.1  |
| OWL                   |  69.70   | —        | —         | —     |
| MiroFlow              |  74.50   | —        | 27.20     | —     |
| Manus                 |  73.30   | —        | —         | —     |
| FlowSearch (Qwen-o4)  |  76.96   | 87.37    | 30.80     | 77.9  |

On GAIA, FlowSearch outperforms OWL, MiroFlow, and Manus. On GPQA-diamond, it achieves 87.37% (versus 85.35% for GPT-5). On HLE, accuracy rises to 30.80%, exceeding leading alternatives. On TRQA, FlowSearch attains 77.9%, a gain of at least 17 percentage points over prior best results [2510.08521].

## 5. Component Analysis and Ablations

Ablation studies isolate the contributions of key architectural elements:

- **Pipeline variants** (from Table 2):

  | Components             | GAIA Avg | GPQA Avg |
  |------------------------|----------|----------|
  | Sequential only        | 55.76    | 71.21    |
  | Flow Planner only      | 61.82    | 73.74    |
  | Flow Planner + Refiner | 76.96    | 87.37    |

The structured planner offers a +6.06% boost on GAIA and +2.53% on GPQA over a sequential baseline; inclusion of the Flow Refiner raises these gains to +15.20% and +15.63%, respectively.

- **Planner model (Table 3):**

  | Planner             | GAIA Avg |
  |---------------------|----------|
  | Qwen-3-8B           | 44.85    |
  | InternPlanner-8B    | 66.06    |
  | Qwen-3-32B          | 64.81    |
  | InternPlanner-32B   | 70.91    |

Fine-tuned InternPlanner LLMs consistently outperform their base counterparts, indicating substantial value from procedure-specific training.

## 6. Systemic Challenges, Domain Limitations, and Future Directions

### 6.1 Systemic and Architectural Challenges

- Agent failure cascades necessitate advanced fault isolation.
- Coordination complexity increases nonlinearly with agent scale, requiring efficient inter-agent communication protocols.
- Unpredictable behaviors demand real-time monitoring and potentially, human oversight.
- Scaling issues (compute and network) reinforce the need for dynamic resource management.
- Secure, privacy-preserving multi-agent communication is imperative.

### 6.2 Domain-Specific Limitations

- Literature coverage remains incomplete; broader and more diverse corpora are needed.
- Hallucination and factual inaccuracies in LLM output underline the importance of external fact-checking and authoritative integration.
- Interoperability with specialized scientific tools is limited; extensible APIs and plugin ecosystems are needed.
- Standard metrics (e.g., Elo-based) may not align with expert evaluation; hybrid assessment modalities are recommended.
- Validation studies have limited cross-disciplinarity and scale.

### 6.3 Prospective Extensions

- Adoption of modular, multi-stage agent architectures (encompassing generation, reflection, ranking, evolution, and meta-review).
- Fusion of modern generative LLMs with classical multi-agent coordination frameworks (e.g., FIPA, Soar, ACT-R).
- Edge and distributed execution for resilience and efficiency.
- Deeper external toolchain integration, notably with scientific simulators and structured knowledge bases.
- Development of standards for reproducibility, provenance, and ethical governance in autonomous research.

A plausible implication is that FlowSearch’s explicit, DAG-centered orchestration and multi-agent parallelism provide a foundation for scalable, adaptive research agents, potentially generalizing beyond current evaluation domains. The open-source codebase (https://github.com/Alpha-Innovator/InternAgent) offers reproducibility and extensibility for further scientific inquiry [2510.08521].

Source: https://www.emergentmind.com/topics/flowsearch