CaveAgent: Transforming LLMs into Stateful Runtime Operators

• URL: http://arxiv.org/abs/2601.01569v1
• Date: Sun, 04 Jan 2026 15:32:47 GMT
• Title: CaveAgent: Transforming LLMs into Stateful Runtime Operators
• Authors: Maohao Ran, Zhenglin Wan, Cooper Lin, Yanting Zhang, Hongyu Xin, Hongwei Fan, Yibo Xu, Beier Luo, Yaxin Zhou, Wangbo Zhao, Lijie Yang, Lang Feng, Fuchao Yang, Jingxuan Wu, Yiqiao Huang, Chendong Ma, Dailing Jiang, Jianbo Deng, Sihui Han, Bo An, Yike Guo, Jun Song,
• Abstract summary: We present CaveAgent, a framework that transforms the paradigm from "LLM-as-Text-Generator" to "LLM-as-As-Runtime-Runtime"<n>CaveAgent achieves a 10.5% success rate improvement on retail tasks and reduces total token consumption by 28.4% in multi-turn scenarios.
• Score: 31.548422546991915
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms. Traditional approaches rely on procedural JSON-based function calling, which often struggles with long-horizon tasks due to fragile multi-turn dependencies and context drift. In this paper, we present CaveAgent, a framework that transforms the paradigm from "LLM-as-Text-Generator" to "LLM-as-Runtime-Operator." We introduce a Dual-stream Context Architecture that decouples state management into a lightweight semantic stream for reasoning and a persistent, deterministic Python Runtime stream for execution. In addition to leveraging code generation to efficiently resolve interdependent sub-tasks (e.g., loops, conditionals) in a single step, we introduce \textit{Stateful Runtime Management} in CaveAgent. Distinct from existing code-based approaches that remain text-bound and lack the support for external object injection and retrieval, CaveAgent injects, manipulates, and retrieves complex Python objects (e.g., DataFrames, database connections) that persist across turns. This persistence mechanism acts as a high-fidelity external memory to eliminate context drift, avoid catastrophic forgetting, while ensuring that processed data flows losslessly to downstream applications. Comprehensive evaluations on Tau$^2$-bench, BFCL and various case studies across representative SOTA LLMs demonstrate CaveAgent's superiority. Specifically, our framework achieves a 10.5\% success rate improvement on retail tasks and reduces total token consumption by 28.4\% in multi-turn scenarios. On data-intensive tasks, direct variable storage and retrieval reduces token consumption by 59\%, allowing CaveAgent to handle large-scale data that causes context overflow failures in both JSON-based and Code-based agents.

Related papers

• AgentSkiller: Scaling Generalist Agent Intelligence through Semantically Integrated Cross-Domain Data Synthesis [30.512393568258105]
  Large Language Model agents demonstrate potential in solving real-world problems via tools, yet generalist intelligence is bottlenecked by scarce high-quality, long-horizon data.<n>We propose AgentSkiller, a fully automated framework synthesizing multi-turn interaction data across realistic, semantically linked domains.
  arXiv  Detail & Related papers  (2026-02-10T03:21:42Z)
• DLLM Agent: See Farther, Run Faster [94.74432470237817]
  Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties.<n>We study this in a controlled setting by instantiatingDLLM and AR backbones within the same agent workflow.<n>We find thatDLLM Agents are on average over 30% faster end to end than AR agents, with some cases exceeding 8x speedup.
  arXiv  Detail & Related papers  (2026-02-07T09:01:18Z)
• Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation [50.22481337087162]
  Referring Video Object (RVOS) aims to segment objects in videos based on textual queries.<n>Refer-Agent is a collaborative multi-agent system with alternating reasoning-reflection mechanisms.
  arXiv  Detail & Related papers  (2026-02-03T14:48:12Z)
• MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering [54.236614097082395]
  We introduce MEnvAgent, a framework for automated Environment construction.<n>MEnvAgent employs a multi-agent Planning-Execution-Verification architecture to autonomously resolve construction failures.<n>MEnvData-SWE is the largest open-source polyglot dataset of realistic verifiable Docker environments to date.
  arXiv  Detail & Related papers  (2026-01-30T11:36:10Z)
• CEDAR: Context Engineering for Agentic Data Science [3.1662160826016756]
  CEDAR is an application for automating data science tasks with an agentic setup.<n>We show that these can be alleviated via effective context engineering.<n>Fault tolerance and context management are introduced via iterative code generation and smart history rendering.
  arXiv  Detail & Related papers  (2026-01-10T16:05:04Z)
• InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents [36.740230738304525]
  InfiAgent keeps the agent's reasoning context strictly bounded regardless of task duration.<n>InfiAgent with a 20B open-source model is competitive with larger proprietary systems.
  arXiv  Detail & Related papers  (2026-01-06T17:35:57Z)
• SCOPE: Prompt Evolution for Enhancing Agent Effectiveness [53.75986399936395]
  Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts.<n>While agents have access to this context, their static prompts lack the mechanisms to manage it effectively.<n>We introduce textbfSCOPE (Self-evolving Context Optimization via Prompt Evolution)<n>We propose a Dual-Stream mechanism that balances tactical specificity (resolving immediate errors) with strategic generality (evolving long-term principles)
  arXiv  Detail & Related papers  (2025-12-17T12:25:05Z)
• AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management [24.465443389008055]
  AgentProg is a program-guided approach for agent context management.<n>It reframes the interaction history as a program with variables and control flow.<n> Experiments on AndroidWorld and our extended long-horizon task suite demonstrate that AgentProg has achieved the state-of-the-art success rates.
  arXiv  Detail & Related papers  (2025-12-11T07:37:38Z)
• Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems [11.42175340352007]
  We introduce SupervisorAgent, a lightweight and modular framework for runtime, adaptive supervision.<n>SupervisorAgent intervenes at critical junctures to proactively correct errors, guide inefficient behaviors, and purify observations.<n>On the challenging GAIA benchmark, SupervisorAgent reduces the token consumption of the Smolagent framework by an average of 29.45% without compromising its success rate.
  arXiv  Detail & Related papers  (2025-10-30T15:12:59Z)
• DeepAgent: A General Reasoning Agent with Scalable Toolsets [111.6384541877723]
  DeepAgent is an end-to-end deep reasoning agent that performs autonomous thinking, tool discovery, and action execution.<n>To address the challenges of long-horizon interactions, we introduce an autonomous memory folding mechanism that compresses past interactions into structured episodic, working, and tool memories.<n>We develop an end-to-end reinforcement learning strategy, namely ToolPO, that leverages LLM-simulated APIs and applies tool-call advantage attribution to assign fine-grained credit to the tool invocation tokens.
  arXiv  Detail & Related papers  (2025-10-24T16:24:01Z)
• CoDA: Agentic Systems for Collaborative Data Visualization [57.270599188947294]
  Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations.<n>Existing approaches, including simple single- or multi-agent systems, often oversimplify the task.<n>We introduce CoDA, a multi-agent system that employs specialized LLM agents for metadata analysis, task planning, code generation, and self-reflection.
  arXiv  Detail & Related papers  (2025-10-03T17:30:16Z)
• AgentSight: System-Level Observability for AI Agents Using eBPF [10.37440633887049]
  Existing tools observe either an agent's high-level intent (via LLM prompts) or its low-level actions (e.g., system calls) but cannot correlate these two views.<n>We introduce AgentSight, an AgentOps observability framework that bridges this semantic gap using a hybrid approach.<n>AgentSight intercepts TLS-encrypted LLM traffic to extract semantic intent, monitors kernel events to observe system-wide effects, and causally correlates these two streams across process boundaries.
  arXiv  Detail & Related papers  (2025-08-02T01:43:39Z)
• PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC [98.82146219495792]
  In this paper, we propose a hierarchical agent framework named PC-Agent.<n>From the perception perspective, we devise an Active Perception Module (APM) to overcome the inadequate abilities of current MLLMs in perceiving screenshot content.<n>From the decision-making perspective, to handle complex user instructions and interdependent subtasks more effectively, we propose a hierarchical multi-agent collaboration architecture.
  arXiv  Detail & Related papers  (2025-02-20T05:41:55Z)
• Get my drift? Catching LLM Task Drift with Activation Deltas [55.75645403965326]
  Task drift allows attackers to exfiltrate data or influence the LLM's output for other users.<n>We show that a simple linear classifier can detect drift with near-perfect ROC AUC on an out-of-distribution test set.<n>We observe that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions.
  arXiv  Detail & Related papers  (2024-06-02T16:53:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.