Large language models (LLMs) often exhibit sycophancy: agreement with user stance even when it conflicts with the model’s opinion. While prior work has mostly studied this in single-agent settings, it remains underexplored in collaborative multi-agent systems. We ask whether awareness of other agents’ sycophancy levels influences discussion outcomes. To investigate this, we run controlled experiments with six open-source LLMs, providing agents with peer sycophancy rankings that estimate each peer’s tendency toward sycophancy. These rankings are based on scores calculated using various static (pre-discussion) and dynamic (online) strategies. We find that providing sycophancy priors reduces the influence of sycophancy-prone peers, mitigates error-cascades, and improves final discussion accuracy by an absolute 10.5%. Thus, this is a lightweight and efficient way to reduce model sycophancy during discussions and subsequently improve downstream accuracy.

Modern networking technologies such as Remote Direct Memory Access (RDMA) promise huge speedups in I/O bound platforms, but software layering overheads must first be overcome. Our paper studies this issue in a system that replicates small data objects using atomic multicast: a case in which internal synchronization is unavoidable, and any delay will be particularly impactful. Spindle, the methodology we propose, entails a series of optimizations including memory polling integrated with novel sender and receiver batching techniques, null-message send logic, and improved multi-thread synchronization. We applied Spindle to Derecho, an open-source library for atomic multicast, and obtained significant performance improvements both for the library itself and for an OMG-compliant avionics DDS layered on it. Derecho’s multicast bandwidth utilization for 10KB messages rose from 1GB/s to 9.7GB/s on a 12.5GB/s network, and it became more robust to delays even as latency dropped by nearly two orders of magnitude. While our focus is on the Derecho library and the OMG DDS, the same techniques should be relevant to databases, file systems, and IoT infrastructures.

Analytics with three-dimensional imagery from drones are driving the next generation of remote monitoring applications. Today, there is an unmet need in providing such analytics in an interactive manner, especially over weak Internet connections, to quickly diagnose and solve problems in the commercial industry space of monitoring assets using drones in remote parts of the world. Existing mechanisms either compromise on the quality of insights by not building 3D images and analyze individual 2D images in isolation, or spend tens of minutes building a 3D image before obtaining and uploading insights. We present Visage, a system that accelerates 3D image analytics by identifying smaller parts of the data that can actually benefit from 3D analytics and prioritizing building, and uploading the localized 3D images for those parts. To achieve this, Visage uses a graph to represent raw 2D images and their relative content overlap, and then identifies the various subgraphs using application knowledge that are good candidates for localized 3D image based insights. We evaluate Visage using data from multiple real deployments and show that it can reduce analytics-latency by up to four orders of magnitude.

Applications with internal substructure are common in the cloud, where many systems are organized as independently logged and replicated subsystems that interact via flows of objects or some form of RPC. Restarting such an application is difficult: a restart algorithm needs to efficiently provision the subsystems by mapping them to nodes with needed data and compute resources, while simultaneously guaranteeing that replicas are in distinct failure domains. Additional failures can occur during recovery, hence the restart process must itself be a restartable procedure. In this paper we present an algorithm for efficiently restarting a service composed of sharded subsystems, each using a replicated state machine model, into a state that (1) has the same fault-tolerance guarantees as the running system, (2) satisfies resource constraints and has all needed data to restart into a consistent state, (3) makes safe decisions about which updates to preserve from the logged state, (4) ensures that the restarted state will be mutually consistent across all subsystems and shards, and (5) ensures that no committed updates will be lost. If restart is not currently possible, the algorithm will await additional resources, then retry.

Multicast patterns are common in cloud computing and datacenter settings. Applications and infrastructure tools such as Spark frequently move large objects around, update files replicated to multiple nodes, or push new versions of programs to compute nodes. Some applications use replication directly, for example to increase fault-tolerance or achieve parallelism. Implementations of Paxos, block chains and other libraries often employ a hand-built reliable multicast as a primitive. Yet operating systems continue to be focused on point-to-point communication solutions such as TCP or RDMA, a hardware layer with TCP-like semantics that offers zero copy transfers, but lacks a reliable multi-destination transfer capability. Our system, RDMC (RDMA Multicast), offers reliable multicast functionality constructed from RDMA unicast. We discuss design choices, present a theoretical analysis of RDMC's robustness to delays and slow network links, and report on experiments that evaluate RDMC over Mellanox RDMA.

No abstract available.

Cloud computing services often replicate data and may require ways to coordinate distributed actions. Here we present Derecho, a library for such tasks. The API provides interfaces for structuring applications into patterns of subgroups and shards, supports state machine replication within them, and includes mechanisms that assist in restart after failures. Running over 100Gbps RDMA, Derecho can send millions of events per second in each subgroup or shard and throughput peaks at 16GB/s, substantially outperforming prior solutions. Configured to run purely on TCP, Derecho is still substantially faster than comparable widely used, highly-tuned, standard tools. The key insight is that on modern hardware (including non-RDMA networks), data-intensive protocols should be built from non-blocking data-flow components.

The coming generation of Internet-of-Things (IoT) applications will process massive amounts of incoming data while supporting data mining and online learning. In cases with demanding real-time requirements, such systems behave as smart memories: a high-bandwidth service that captures sensor input, processes it using machine-learning tools, replicates and stores "interesting" data (discarding uninteresting content), updates knowledge models, and triggers urgently-needed responses.

Bounded-rate multi-mode systems are hybrid systems that can switch among a finite set of modes. Its dynamics is specified by a finite number of real-valued variables with mode-dependent rates that can vary within given bounded sets. Given an arbitrary piecewise linear trajectory, we study the problem of following the trajectory with arbitrary precision, using motion primitives given as bounded-rate multi-mode systems. We give an algorithm to solve the problem and show that the problem is co-NP complete. We further prove that the problem can be solved in polynomial time for multi-mode systems with fixed dimension. We study the problem with dwell-time requirement and show the decidability of the problem under certain positivity restriction on the rate vectors. Finally, we show that introducing structure to the multi-mode systems leads to undecidability, even when using only a single clock variable.