Self-Programmed Execution for Language-Model Agents
At the heart of existing language model agents is a fixed orchestrator program responsible for the state transition between consecutive turns. This paper introduces self-programmed execution (SPE), an agent architecture in which the model completion is itself the orchestrator program, and the harness evaluates this program but does not impose its own orchestration policy. I formalize this idea using agentic machines: an SPE state is one from which a model completion can load any state of an embedded copy of the machine, meaning that it is subject to no fixed turn-to-turn orchestration policy. Realizing SPE in practice is nontrivial because the same data is both model context and executable program. I therefore introduce Spell, a Lisp-based language in which programs can edit and re-evaluate themselves, and effectful expressions like model invocations are structured such that re-evaluating an edited program does not replay its side effects. Experiments with existing models, not trained for SPE or Spell, show that frontier models can operate in this regime and accomplish challenging agentic tasks. These results demonstrate how an LM can act as an agent without any fixed orchestration policy, and they raise the question of what self-orchestration strategies might be learned by a model trained for self-programmed execution. Code is available at https://github.com/lukejoconnor/spell .
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Deception in LLMs: Self-Preservation and Autonomous Goals in Large Language Models
Recent advances in Large Language Models (LLMs) have incorporated planning and reasoning capabilities, enabling models to outline steps before execution and provide transparent reasoning paths. This enhancement has reduc…
The Struggle for Existence: Time, Memory and Bloat
Combining a spatiotemporal, multi-agent based model of a foraging ecosystem with linear, genetically programmed rules for the agents' behaviors results in implicit, endogenous, objective functions and selection algorithm…
AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
Large Language Model (LLM)-based agentic systems, often comprising multiple models, complex tool invocations, and orchestration protocols, substantially outperform monolithic agents. Yet this very sophistication amplifie…
Reinforcement LearningSocial Catalysts, Not Moral Agents: The Illusion of Alignment in LLM Societies
The rapid evolution of Large Language Models (LLMs) has led to the emergence of Multi-Agent Systems where collective cooperation is often threatened by the "Tragedy of the Commons." This study investigates the effectiven…
Embedding Autonomous Agents in Resource-Constrained Robotic Platforms
Many embedded devices operate under resource constraints and in dynamic environments, requiring local decision-making capabilities. Enabling devices to make independent decisions in such environments can improve the resp…