Structured Cognitive Loop for Behavioral Intelligence in Large Language Model Agents
This addresses the problem of coherence and predictability in autonomous agents for researchers and practitioners, though it is incremental as it builds on existing frameworks like ReAct and LangChain.
The paper tackles the architectural challenges of using large language models as autonomous agents for multi-step tasks by proposing the Structured Cognitive Loop (SCL), which separates cognition, memory, and control, resulting in an average task success rate of 86.3% compared to 70.5-76.8% for baselines.
Large language models have advanced natural language understanding and generation, but their use as autonomous agents introduces architectural challenges for multi-step tasks. Existing frameworks often mix cognition, memory, and control in a single prompt, reducing coherence and predictability. The Structured Cognitive Loop (SCL) is proposed as an alternative architecture that separates these functions. In SCL, the language model handles cognition, memory is stored externally, and execution is guided by a lightweight controller within a goal-directed loop. This design allows intermediate results to be recorded and verified before actions are taken, improving traceability and evaluation. SCL is evaluated against prompt-based baselines such as ReAct and LangChain agents across three tasks: travel planning, conditional email drafting, and constraint-guided image generation. Under matched settings, SCL achieves an average task success rate of 86.3 percent, compared with 70.5 to 76.8 percent for baselines. It also shows higher goal fidelity, fewer redundant calls, and reduced unsupported assertions. These results indicate that separating cognition, memory, and control can enhance reliability and interpretability without relying on larger models or heavier prompts. The findings should be regarded as preliminary evidence, with broader tests across model families and task domains planned for future work.