---
title: 'RP-ReAct: Decoupled Reasoning & Execution'
url: https://www.emergentmind.com/topics/rp-react-reasoner-planner-react-4bdaddb1-c3c5-4fd2-93c3-907ba4f78f47
type: topic
---

# RP-ReAct: Decoupled Reasoning & Execution

RP-ReAct (Reasoner Planner–ReAct) is a multi-agent framework for complex tool-augmented reasoning and execution, characterized by explicit architectural separation between high-level task decomposition and low-level iterative interaction with tools. The central innovation is the decoupling of strategic planning (reasoner-planner) from micro-level tool invocation (reactive executor), a paradigm applicable across enterprise automation, robotics, code generation, and general multi-tool LLM reasoning. The approach addresses key limitations of monolithic plan–execute agent designs, including poor generalization, token context overflow, and trajectory instability, by introducing modular supervision, global planning, and formal context management [2512.03560], [2511.10037], [2510.08665].

## 1. Architectural Principles and Agent Roles

RP-ReAct systematically decomposes the agentic workflow along two axes: reasoning/planning and acting. At its core are two (or more) specialized agents:

- **Reasoner-Planner Agent (RPA):**  
  Receives user tasks and, using a large reasoning model (LRM), generates an ordered sequence of abstract sub-questions or constructs a global plan. The RPA supervises the overall process, consuming the results of execution, validating expectations, and engaging in diagnosis and replanning upon observed failure or deviation [2512.03560].
  
- **Proxy Execution Agent (PEA):**  
  Receives subtasks from the RPA and executes them by dynamically interacting with tool APIs (e.g., SQL interpreters, code evaluators, search engines) via a ReAct-style loop—alternating between "Thought", "Action", "Observation" phases. PEAs are isolated from the global plan and focus solely on concrete micro-execution [2512.03560], [2510.08665].

Alternate forms include frameworks where the planner emits a global DAG over tools (Planner-Centric RP-ReAct [2511.10037]), or where the pipeline is further specialized with agents for planning, searching, code generation, and extraction (RA-Gen [2510.08665]).

This design ensures trajectory stability, prevents context overload in the reasoning agent, and supports both sequential and parallel tool use. In enterprise applications, this separation also simplifies compliance by making sensitive tool calls occur in a sandbox isolated from planning logic [2512.03560].

## 2. Formal Workflow and Context Management

The execution pipeline in RP-ReAct is governed by tightly specified algorithms for both agent roles:

- **RPA (Supervision and Planning):**  
  Iteratively constructs a plan by querying the LRM for the next abstract step, submits each to the PEA, and incorporates execution results. On failure, the RPA invokes self-diagnosis and replanning, generating corrective queries and updating its plan history [2512.03560].
  
- **PEA (ReAct Executor):**  
  Maintains a scratchpad recording reasoning traces and tool observations. At each step, it emits a sequential "Thought", chooses an "Action" (tool call), observes the result, and appends the triplet to the scratchpad. Termination is monitored by explicit finish signals in action or observation [2512.03560].

A key architectural element is **context window management**. When a PEA encounters a tool output whose token size exceeds a pre-defined threshold \( T \), the result is truncated for in-context preview, and the full output is externalized to a variable in the execution environment. The RPA receives only a summary and reference, avoiding catastrophic token overflow [2512.03560]. This is crucial for open-weight LRMs with restricted context sizes.

In planner-centric variants, the global plan is represented as a Directed Acyclic Graph (DAG) over tools, enabling parallel execution and efficient aggregation of results [2511.10037].

## 3. Learning and Optimization Strategies

RP-ReAct frameworks leverage both supervised and reinforcement learning protocols to enhance planning quality:

- **Supervised Fine-Tuning (SFT):**  
  The planner LLM is fine-tuned on a dataset of (query, plan) pairs (e.g., the ComplexTool-Plan dataset in [2511.10037]), optimizing the likelihood of emitting the correct execution DAG.
  
- **Reinforcement Learning (GRPO):**  
  After SFT, Group Relative Policy Optimization (GRPO) is applied on a filtered hard set, maximizing hierarchical rewards—penalizing syntax errors, cycles, disconnected plans, and incentivizing correct tool/edge selection [2511.10037].

In the code generation setting (RA-Gen), control over agent behavior and safety is augmented by user-settable constraints (e.g., maximum search depth, allowed tools), and by explicit static validation (e.g., CodeQL checks) before code release [2510.08665].

## 4. Benchmarking and Quantitative Performance

RP-ReAct frameworks have been evaluated on challenging multi-tool benchmarks:

- **ToolQA [2512.03560]:**  
  Complex, multi-domain question answering requiring up to 13 tool functions per instance. RP-ReAct achieves superior accuracy—particularly on hard tasks requiring deep, sequential reasoning (+10–20 points on large models)—and demonstrates 50% lower accuracy standard deviation across models compared to ReAct or Reflexion baselines. Gains stem from reduced "trajectory drift" and robust context handling.

- **StableToolBench [2511.10037]:**  
  In a planner-centric RP-ReAct with the Qwen3-8B (RL) planner and GPT-4o executor, the framework yields 59.8% Solvable Pass Rate (SoPR), whereas GPT-4 ReAct achieves only 48.2%. RP-ReAct also requires significantly fewer inference steps (2.29 avg.) than iterative ReAct (~4.2 avg.), reflecting the efficiency of global planning.

- **SVEN (Security/Code Generation) [2510.08665]:**  
  RA-Gen, an RP-ReAct instance, attains a 94.8% security rate and 95.8% pass rate on vulnerability-patching tasks. It outperforms base GPT-4 and Gemini1.0 Pro, with explicit traceability for every step.

A common finding is that RP-ReAct requires large LRMs with substantial base reasoning capacity; model sizes below 7–8B parameters do not reliably solve complex benchmarks [2512.03560].

## 5. Theoretical Foundations and Extensions

Early formalizations of the RP-ReAct paradigm are grounded in high-level transition models and reactive policies with planning [1603.09495]. In these, execution proceeds through (a) a reasoner selecting subgoals based on clustered abstract states, and (b) an integrated planner computing plans to reach these subgoals. Theoretical analysis encompasses the soundness and completeness of plan synthesis, complexity (PSPACE in general), and properties of state clustering.

Later systems add online learning, partial observability, and multi-agent configurations. For example, RAE+UPOM+Learning interleaves deliberative acting and online planning with operational models, using Monte Carlo Tree Search and domain-learned heuristics to optimize real-time acting efficiency [2010.01909].

Controllability, safety, and interpretability are reinforced in code generation contexts by explicit agent modularity, transparent reasoning traces, and static verification gates [2510.08665].

## 6. Limitations and Future Trajectories

Current RP-ReAct variants are subject to several limitations:

- Generalization is bounded by available datasets (ToolQA/ComplexTool-Plan) and the absence of broader, more diverse benchmarks (e.g., OfficeBench, Mint) [2512.03560].
- No supervised or reinforcement tuning has yet been applied to RPA and PEA in the original enterprise setting, leaving potential gains untapped [2512.03560].
- Context threshold and model temperature require further systematic exploration; integration of more advanced summarization and memory mechanisms is a prospective extension [2512.03560].
- Robustness with small models and real-time multi-agent deployments remains an open area, as does quantitative evaluation against traditional agent control architectures [2501.10106].
- Global plans may become intractably complex for very large toolsets without further abstraction, pruning strategies, or hierarchical decomposition.

Research trends indicate future directions including symbolic-abstraction refinement, richer plan forms (e.g., contingent, hierarchical), multi-agent orchestration, and explicit learning/refinement of reasoning and planning components over time [1603.09495], [2511.10037].

## 7. Cross-Domain Relevance

RP-ReAct's architecture—decoupling global reasoning from local execution—has been broadly instantiated: from complex enterprise automation [2512.03560], to multi-agent code generation with formal safety guarantees [2510.08665], to NPC control in simulated environments [2501.10106], to planner-centric tool reasoning with parallel execution over DAGs [2511.10037], and foundationally to high-level policy synthesis in action-languages [1603.09495]. A plausible implication is that this modular decoupling is converging as a standard design pattern in LLM-augmented agentic reasoning, especially under context, compliance, and generalization constraints endemic to complex real-world domains.

Source: https://www.emergentmind.com/topics/rp-react-reasoner-planner-react-4bdaddb1-c3c5-4fd2-93c3-907ba4f78f47