Related papers: An Asynchronous Scheme for Rollback Recovery in Me…
Reversible debuggers and process replay have been developed at least since 1970. This vision enables one to execute backwards in time under a debugger. Two important problems in practice are that, first, current reversible debuggers are…
Large language model (LLM)-based coding agents increasingly rely on external memory to reuse prior debugging experience, repair traces, and repository-local operational knowledge. However, retrieved memory is useful only when the current…
Coded computation techniques provide robustness against straggling workers in distributed computing. However, most of the existing schemes require exact provisioning of the straggling behaviour and ignore the computations carried out by…
Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restore (C/R) of this state is needed for fault tolerance, spot execution, RL rollout branching,…
High-performance computing on shared-memory/multi-core architectures could suffer from non-negligible performance bottlenecks due to coordination algorithms, which are nevertheless necessary to ensure the overall correctness and/or to…
This paper considers cooperative Multi-Agent Reinforcement Learning, focusing on emergent communication in settings where multiple pairs of independent learners interact at varying frequencies. In this context, multiple distinct and…
Asynchronous reinforcement learning improves rollout throughput for large language model agents by decoupling sample generation from policy optimization, but it also introduces a critical failure mode for PPO-style off-policy correction. In…
We study how to distribute trace languages in a setting where processes communicate via reconfigurable communication channels. That is, the different processes can connect and disconnect from channels at run time. We restrict attention to…
Large language model agents increasingly depend on memory to sustain long horizon interaction, but existing frameworks remain limited. Most expose only a few basic primitives such as encode, retrieve, and delete, while higher order…
Large language models (LLMs) have made a profound impact across various fields due to their advanced capabilities. However, training these models at unprecedented scales requires extensive AI accelerator clusters and sophisticated…
Session types using affinity and exception handling mechanisms have been developed to ensure the communication safety of protocols implemented in concurrent and distributed programming languages. Nevertheless, current affine session types…
Erasure coding techniques are getting integrated in networked distributed storage systems as a way to provide fault-tolerance at the cost of less storage overhead than traditional replication. Redundancy is maintained over time through…
Large language models (LLMs) have achieved impressive performance in code generation recently, offering programmers revolutionary assistance in software development. However, due to the auto-regressive nature of LLMs, they are susceptible…
We consider a two-user random access system in which each user independently selects a coding scheme from a finite set for every message, without sharing these choices with the other user or with the receiver. The receiver aims to decode…
Mutual exclusion (ME) is one of the most commonly used techniques to handle conflicts in concurrent systems. Traditionally, mutual exclusion algorithms have been designed under the assumption that a process does not fail while…
Since the introduction of the GRPO algorithm, reinforcement learning (RL) has attracted increasing attention for LLM post-training, yet training efficiency remains a critical challenge. In mainstream RL frameworks, inference and training…
Retrieval-based conversation systems generally tend to highly rank responses that are semantically similar or even identical to the given conversation context. While the system's goal is to find the most appropriate response, rather than…
Coroutines are experiencing a renaissance as many modern programming languages support the use of cooperative multitasking for highly parallel or asynchronous applications. One of the greatest advantages of this is that concurrency and…
The optimal fault-tolerance achievable by any protocol has been characterized in a wide range of settings. For example, for state machine replication (SMR) protocols operating in the partially synchronous setting, it is possible to…
Memory reclamation for lock-based data structures is typically easy. However, it is a significant challenge for lock-free data structures. Automatic techniques such as garbage collection are inefficient or use locks, and non-automatic…