distributed computing engineers

Abstract: Low Earth orbit (LEO) satellites increasingly perform time-critical onboard processing, yet heterogeneous computing capabilities, rapidly changing inter-satellite links (ISLs) and uncertain neighbor behavior make decentralized task offloading difficult under partial observations. This paper presents ORCA, an architecture of Onboard Reflective Collaborative Agents for autonomous onboard task offloading. ORCA organizes offloading decisions into a four-Agent \emph{Perceive}$\rightarrow$\emph{Reason}$\rightarrow$ \emph{Act}$\rightarrow$\emph{Learn} loop. It aims to improve efficiency and reliability in dynamic, heterogeneous, and unreliable LEO satellite networks. The simulation results of a heterogeneous 60-satellite Walker-delta constellation demonstrates that ORCA delivers competitive system efficiency in cooperative settings while achieving superior task-success robustness and offloading reliability under previously unseen malicious node behavior, indicating that outcome-grounded reflection can improve the reliability of decentralized onboard offloading without centralized runtime coordination.

Abstract: In analog coded computing, encoding basis functions are typically chosen to guarantee exact reconstruction and improve numerical stability. However, the same basis functions also determine the statistical geometry of the observations available to colluding workers, and hence directly influence the privacy of the underlying data. This suggests that basis selection should not be viewed solely as a reconstruction or numerical conditioning problem, but rather as a joint privacy and accuracy co-design problem. Motivated by this observation, we revisit Analog Lagrange Coded Computing (ALCC) and show that the full orthogonality constraints imposed by the conventional Lagrange basis are stronger than what is required for exact recovery. We retain only the interpolation constraints necessary for the data bearing basis functions and require the noise bearing basis functions merely to vanish at the data recovery points. This yields a parameterized family of generalized polynomial encoding bases that preserves exact reconstruction while introducing additional design degrees of freedom. We then derive a basis-dependent characterization of differential privacy for colluding workers and formulate a privacy-calibrated numerical optimization problem that jointly selects the data and noise basis functions to reduce reconstruction error while satisfying a prescribed \((ε,δ)\)-DP requirement. The resulting framework therefore treats the encoding basis itself as a privacy-design variable, rather than selecting a fixed closed-form basis a priori. The same design philosophy is also compatible with alternative privacy metrics such as mutual-information leakage. Numerical results show that, at the same privacy level, optimized basis functions substantially reduce floating-point reconstruction error relative to conventional ALCC.

Abstract: Between them, the members of a research group or a circle of friends own several consumer computers, none large enough to run a capable large language model. Existing systems pool such capacity across open swarms anyone may join, which a group admitting only trusted machines cannot use. Bounding membership removes what they depend on: a swarm holds each part of the model on several peers and routes around a slow one. A bounded session must use every device it admits. Its pipeline advances at the pace of whichever device received a share it cannot serve quickly, so the division has to be right before serving begins. We propose Kafila, whose protocol assembles a ring from behind NATs, preferring direct paths and relaying where traversal fails, while its planner measures each device's memory bandwidth, capacity and reachability, divides the model exactly for a fixed ring order, and places the head, which holds the embedding and output projection, together with that division rather than beforehand. On machines with different capabilities across three fleets, from a shared LAN to five devices spanning two continents, Kafila shortens the slowest pipeline stage by up to $5.2\times$ against the even split of pipeline parallelism, as in GPipe, and up to $3\times$ against the memory-proportional split of personal-device inference, as in exo, keeps 75 to 87 per cent of the committed hardware doing work where those divisions fall below half, and serves a model no uniform split can place on the fleet at all. What that is worth to a user depends on how much of a token is computation rather than network. Where the members share a network the same division returns $1.56\times$ the throughput of a uniform split and $1.25\times$ of a memory-proportional one, and under four concurrent users that lead compounds to $3.2\times$ rather than fading, each user served at almost the rate of one.

Abstract: A multi-agent system can reduce latency on complex tasks by executing work concurrently. Several pioneering harness frameworks support multi-agent systems. However, the scalability of current multi-agent harnesses is often constrained by a central orchestrator's capacity to allocate tasks and coordinate workers. To address this limitation, we introduce Agensh, a scalable self-organized multi-agent harness without a central orchestrator: concurrent workers execute a multi-agent cooperation loop, continuously gathering context, claiming and self-assigning sub-tasks, taking action and sharing findings, verifying results, and merging progress in an asynchronous manner. The loop is supported by the agentic organization infrastructure comprising three components: a shared workspace holds proposed, ongoing, and completed work; a message interface lets workers communicate; and shared context retains reusable findings and work intentions. To test the scalability of Agensh, we evaluate it on the five hardest ProgramBench tasks with GPT-5.6-sol (high). Scaling from 1 to 128 agents raises the mean final test-pass rate from 19.31% to 28.78%, an approximately 49% relative improvement. Larger organizations reach comparable test-pass rates earlier. On pandoc, scaling from 1 to 1,024 agents raises the final test-pass rate from 33.89% to 55.06%. Worker trajectories further show that different forms of self-organized cooperation gradually emerges and standardizes as the organization grows. These results reveal the number of agents as a new scaling dimension for multi-agent organizations to expand the frontier of general intelligence, offering a practical solution for complex tasks under hard latency constraints or time budgets.

Abstract: Johnson graphs $J(n,k)$ are a classical family of highly symmetric networks known to be Hamiltonian-connected in the fault-free setting. In this paper, we investigate their Hamiltonian connectivity under three failure models, namely general edge faults, matching faults, and vertex faults. For general edge faults, we prove that $J(n,k)$ remains Hamiltonian-connected after the deletion of any set of at most $k(n-k)-3$ edges for $n\geq4$. Since $J(n,k)$ is $k(n-k)$-regular, this attains the natural degree-based upper bound for Hamiltonian connectivity. We then consider matching faults, which exclude the concentration of multiple faulty links at a single vertex and permit substantially larger fault sets. We show that $J(n,k)$ remains Hamiltonian-connected after the deletion of an arbitrary matching for $n\geq5$, including a perfect matching whenever one exists. For vertex failures, we prove that $J(n,k)$ is $(n-2)$-vertex-fault-tolerant Hamiltonian-connected for $n\geq5$. All three results are constructive and lead to recursive fault-tolerant Hamiltonian routing algorithms. Simulation results on Johnson graphs with up to $12{,}870$ vertices further show that the routing algorithms successfully construct fault-free Hamiltonian paths for all tested source-destination pairs, with measured execution times exhibiting near-linear growth with network size. These results establish a unified fault-tolerant Hamiltonian-connectivity framework for Johnson graphs under different failure patterns.