arXiv AI

Architecting Conversational Data Systems for Stateless LLM APIs: The Hydration Proxy Pattern

The paper introduces the Hydration Proxy Pattern, an architectural approach that separates session persistence from the reasoning engine in conversational AI systems. This pattern allows enterprise platforms to maintain sovereignty over conversational data while still leveraging stateless LLM APIs for scalability. Additionally, the authors propose the Context Stabilization Mandate to balance sovereign state management with key‑value caching.

arXiv AI
Aug 28

SKILL.state: Scalable Long-Horizon Agent Skills

SKILL.state is a new runtime architecture for large language model agents that replaces the traditional append‑only conversational history with an explicit, mutable execution state. At each step the model receives only the immutable skill specification, the current structured state, and the latest observation, discarding intermediate reasoning after validating state updates. Experiments across datasets, models, and environments show that SKILL.state improves task accuracy and significantly reduces cumulative token consumption, proving that explicit execution state is a scalable, architecture‑agnostic abstraction for long‑horizon agent skills.

By Sanket Badhe, Priyanka Tiwari, Jonghyun Chung
arXiv Computation and Language
Sep 1

LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents

The paper argues that large language models (LLMs) lack a private working memory, which is essential for tasks that require hidden state, such as interactive games. It introduces Private State Interactive Tasks (PSITs) and proves that chat-based LLMs cannot maintain a secret state while producing consistent public responses. Empirical tests confirm that standard LLMs and retrieval-based baselines fail, while a new architecture with explicit private memory succeeds.

By Davide Baldelli, Ali Parviz, Amal Zouaq, Sarath Chandar
arXiv AI
Aug 24

PrimeAgentOrchestrator: Memory-Primed Agent Spawning for Personal AI Infrastructure

PrimeAgentOrchestrator (PAO) is a system that spawns new instances of Claude Code, Anthropic’s terminal-based coding agent, pre‑loaded with relevant memories from a user’s personal databases. PAO queries a PostgreSQL entity‑observation database and a Cloudflare Worker semantic search index in parallel, fuses the results, and injects the compiled briefing into the agent’s filesystem to exploit its auto‑read configuration. The paper reports four months of deployment, detailing three generations of context delivery mechanisms, the failure modes that prompted each redesign, and the engineering tradeoffs involved in integrating heterogeneous memory systems instead of building a unified one.

By Myron Koch (Peak Summit Labs)
arXiv AI
Jun 30

CaveAgent: Transforming LLMs into Stateful Runtime Operators

arXiv:2601. 01569v4 Announce Type: replace Abstract: LLM-based agents are increasingly capable of complex task execution, yet current agentic systems remain constrained by text-centric paradigms that struggle with long-horizon tasks due to fragile multi-turn dependencies and context drift.

By 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, Yusen Huang, Dailing Jiang, Jianbo Deng, Sirui Han, Yang You, Bo An, Yike Guo, Jun Song
arXiv AI
Sep 2

ContextPipe: Database-Inspired Context Assembly for Long-Horizon Agents

ContextPipe is a database-inspired framework for assembling context in long-horizon large language model agents. It treats context assembly like relational query execution, using a five-phase pipeline—Plan, Bind, Optimize, Execute, Feedback—backed by a structured catalog, deterministic cache-aware optimizer, and EXPLAIN ANALYZE tracing. In a preliminary evaluation on the SWE-bench Pro Qutebrowser subset, ContextPipe reduced token volume by 31%, LLM calls by 23%, and response time by 9% compared to an append-only policy, though it lowered KV cache-hit ratio.

By Peng Xu, Zuyu Zhang, Yuze Sun, Feng Tian, Long Wang, Chen Zhang