Context Compaction Theory

Large Language Models (LLMs) have a bounded context window. The context window is the maximum input size an LLM can consume for a single inference. AI agents rely on a process called context compaction to fit their state within the context window when calling an LLM. Despite its ubiquity, context compaction has received essentially no formal analysis. In this paper, we initiate a formal study of context compaction. We first introduce a framework consisting of two games that capture the two algorithmic strategies for context compaction used by contemporary AI agents in practice. The Context Selection Game models context compaction algorithms that select a subset of an agent's accumulated state to retain. The Context Generation Game models context compaction algorithms that summarize an agent's state by an arbitrary message of bounded length. We then prove an equivalence between the Context Generation Game and one-way communication complexity. The minimum context compaction budget for answering a set of queries within a target error is equal to the one-way communication complexity of the induced communication problem at the same error. Known bounds from communication complexity therefore transfer directly to context compaction. We also show that the Context Selection Game corresponds to a restricted class of one-way communication protocols. Any gap between selection and generation is therefore a gap between two classes of communication protocols. We prove that there exists a set of queries for which generation needs strictly less budget than selection. The equivalence between the Context Generation Game and one-way communication also lets us measure how well a deployed context compaction algorithm performs on a query relative to the optimal strategy. As an example, we present a case study that evaluates Anthropic's context compaction endpoint on set membership queries.

DRCY: Agentic Hardware Design Reviews

Hardware design errors discovered after fabrication require costly physical respins that can delay products by months. Existing electronic design automation (EDA) tools enforce structural connectivity rules. However, they cannot verify that connections are \emph{semantically} correct with respect to component datasheets. For example, that a symbol's pinout matches the manufacturer's specification, or that a voltage regulator's feedback resistors produce the intended output. We present DRCY, the first production-ready multi-agent LLM system that automates first-pass schematic connection review by autonomously fetching component datasheets, performing pin-by-pin analysis against extracted specifications, and posting findings as inline comments on design reviews. DRCY is deployed in production on AllSpice Hub, a collaborative hardware design platform, where it runs as a CI/CD action triggered on design review submissions. DRCY is used regularly by major hardware companies for use-cases ranging from multi-agent vehicle design to space exploration. We describe DRCY's five-agent pipeline architecture, its agentic datasheet retrieval system with self-evaluation, and its multi-run consensus mechanism for improving reliability on safety-critical analyses

Orla: A Library for Serving LLM-Based Multi-Agent Systems

We introduce Orla, a library for constructing and running LLM-based agentic systems. Modern agentic applications consist of workflows that combine multiple LLM inference steps, tool calls, and heterogeneous infrastructure. Today, developers typically build these systems by manually composing orchestration code with LLM serving engines and tool execution logic. Orla provides a general abstraction that separates request execution from workflow-level policy. It acts as a serving layer above existing LLM inference engines: developers define workflows composed of stages, while Orla manages how those stages are mapped, executed, and coordinated across models and backends. It provides agent-level control through three mechanisms: a stage mapper, which assigns each stage to an appropriate model and backend; a workflow orchestrator, which schedules stages and manages their resources and context; and a memory manager, which manages inference state such as the KV cache across workflow boundaries. We demonstrate Orla with a customer support workflow that exercises many of its capabilities. We evaluate Orla on two datasets, showing that stage mapping improves latency and cost compared to a single-model vLLM baseline, while workflow-level cache management reduces time-to-first-token.

Whistledown: Combining User-Level Privacy with Conversational Coherence in LLMs

Users increasingly rely on large language models (LLMs) for personal, emotionally charged, and socially sensitive conversations. However, prompts sent to cloud-hosted models can contain personally identifiable information (PII) that users do not want logged, retained, or leaked. We observe this to be especially acute when users discuss friends, coworkers, or adversaries, i.e., when they spill the tea. Enterprises face the same challenge when they want to use LLMs for internal communication and decision-making. In this whitepaper, we present Whistledown, a best-effort privacy layer that modifies prompts before they are sent to the LLM. Whistledown combines pseudonymization and $ε$-local differential privacy ($ε$-LDP) with transformation caching to provide best-effort privacy protection without sacrificing conversational utility. Whistledown is designed to have low compute and memory overhead, allowing it to be deployed directly on a client's device in the case of individual users. For enterprise users, Whistledown is deployed centrally within a zero-trust gateway that runs on an enterprise's trusted infrastructure. Whistledown requires no changes to the existing APIs of popular LLM providers.

A Privacy Model for Classical & Learned Bloom Filters

The Classical Bloom Filter (CBF) is a class of Probabilistic Data Structures (PDS) for handling Approximate Query Membership (AMQ). The Learned Bloom Filter (LBF) is a recently proposed class of PDS that combines the Classical Bloom Filter with a Learning Model while preserving the Bloom Filter's one-sided error guarantees. Bloom Filters have been used in settings where inputs are sensitive and need to be private in the presence of an adversary with access to the Bloom Filter through an API or in the presence of an adversary who has access to the internal state of the Bloom Filter. Prior work has investigated the privacy of the Classical Bloom Filter providing attacks and defenses under various privacy definitions. In this work, we formulate a stronger differential privacy-based model for the Bloom Filter. We propose constructions of the Classical and Learned Bloom Filter that satisfy $(\epsilon, 0)$-differential privacy. This is also the first work that analyses and addresses the privacy of the Learned Bloom Filter under any rigorous model, which is an open problem.