Mixture-of-Experts (MoE) models have recently gained steam in achieving the state-of-the-art performance in a wide range of tasks in computer vision and natural language processing. They effectively expand the model capacity while incurring a minimal increase in computation cost during training. However, deploying such models for inference is difficult due to their large model size and complex communication pattern. In this work, we provide a characterization of two MoE workloads, namely Language Modeling (LM) and Machine Translation (MT) and identify their sources of inefficiencies at deployment. We propose three optimization techniques to mitigate sources of inefficiencies, namely (1) Dynamic gating, (2) Expert Buffering, and (3) Expert load balancing. We show that dynamic gating improves maximum throughput by 6.21-11.55$\times$

The Price of Anarchy (PoA) is a standard metric for quantifying inefficiency in socio-technical systems, widely used to guide policies like traffic tolling. Conventional PoA analysis relies on exact numerical costs. However, in many settings, costs represent agents' preferences and may be defined only up to possibly arbitrary scaling and shifting, representing informational and modeling ambiguities. We observe that while such transformations preserve equilibrium and optimal outcomes, they change the PoA value. To resolve this issue, we rely on results from Social Choice Theory and define the Invariant PoA. By connecting admissible transformations to degrees of comparability of agents' costs, we derive the specific social welfare functions which ensure that efficiency evaluations do not depend on arbitrary rescalings or translations of individual costs. Case studies on a toy example and the Zurich network demonstrate that identical tolling strategies can lead to substantially different efficiency estimates depending on the assumed comparability. Our framework thus demonstrates that explicit axiomatic foundations are necessary in order to define efficiency metrics and to appropriately guide policy in large-scale infrastructure design robustly and effectively.

Performance bugs are inefficiencies in software that waste computational resources without causing functional failures, making them particularly challenging to detect and fix. While recent advances in Software Engineering agents have shown promise in automated bug fixing, existing benchmarks primarily focus on functional correctness and fail to evaluate agents' abilities to identify and resolve non-functional issues like performance bugs. We introduce PerfBench, a benchmark comprising 81 real-world performance bug-fixing tasks from popular .NET repositories on GitHub. Unlike existing benchmarks that rely on pre-existing test suites, PerfBench features a novel evaluation harness that allows agents to generate their own performance benchmarks and validates fixes by comparing execution metrics collected for developer fix and agent fix. Each task in PerfBench is derived from actual developer fixes linked to performance-related issues, which are then verified by human experts, ensuring real-world relevance. Our evaluation reveals that current state-of-the-art coding agents struggle with performance optimization tasks, with baseline OpenHands agent achieving only a ~3% success rate on our benchmark. We develop OpenHands-Perf-Agent, which incorporates performance-aware tooling and instructions and achieves a ~20% success rate on the benchmark. We show that by ensuring the agent has proper instructions to benchmark its changes and tooling for benchmark output processing, we can improve the agent performance significantly, but room for improvement still remains. PerfBench provides a challenging test set for furthering the capabilities of agents in fixing performance issues.

Agentic systems are modern software systems: they consist of orchestrated modules, expose interfaces, and are deployed in software pipelines. Unlike conventional programs, their execution (i.e., trajectories) is inherently stochastic and adaptive to the problem they are solving. Evaluation of such systems is often outcome-centric, judging their performance based on success or failure at the final step. This narrow focus overlooks detailed insights about such systems, failing to explain how agents reason, plan, act, or change their strategies over time. Inspired by the structured representation of conventional software systems as graphs, we introduce Graphectory to systematically encode the temporal and semantic relations in such software systems. Graphectory facilitates the design of process-centric metrics and analyses to assess the quality of agentic workflows independent of final success. Using Graphectory, we analyze 4000 trajectories of two dominant agentic programming workflows, namely SWE-agent and OpenHands, with a combination of four backbone Large Language Models (LLMs), attempting to resolve SWE-bench Verified issues. Our fully automated analyses reveal that: (1) agents using richer prompts or stronger LLMs exhibit more complex Graphectory, reflecting deeper exploration, broader context gathering, and more thorough validation before patch submission; (2) agents' problem-solving strategies vary with both problem difficulty and the underlying LLM -- for resolved issues, the strategies often follow coherent localization-patching-validation steps, while unresolved ones exhibit chaotic, repetitive, or backtracking behaviors; (3) even when successful, agentic programming systems often display inefficient processes, leading to unnecessarily prolonged trajectories.

Abstract--The rapid adoption of electric vehicles (EVs) introduces major challenges for decentralized charging control. Existing decentralized approaches efficiently coordinate a large number of EVs to select charging stations while reducing energy costs, preventing power peak and preserving driver privacy. These situations create competition for limited charging slots, resulting in long queues and reduced driver comfort. T o address these limitations, we propose a novel collective learning-based coordination framework that allows EVs to balance individual comfort on their selections against system-wide efficiency, i.e., the overall queues across all stations. In the framework, EVs are recommended for adaptive charging behaviors that shift priority between comfort and efficiency, achieving Pareto-optimal trade-offs under varying station capacities and dynamic spatiotemporal EV distribution. Experiments using real-world data from EVs and charging stations show that the proposed approach outperforms baseline methods, significantly reducing travel and queuing time. The results reveal that, under uncertain charging conditions, EV drivers that behave selfishly or altruistically at the right moments achieve shorter waiting time than those maintaining moderate behavior throughout. Our findings under high fractions of station outages and adversarial EVs further demonstrate improved resilience and trustworthiness of decentralized EV charging infrastructure. LECTRIC vehicles (EVs) are becoming a preferred option in intelligent transportation systems due to their energy efficiency and reduced emissions, critical in addressing environmental concerns and fuel shortages. According to recent global market reports, EV sales are projected to surpass 17 million units in 2024 (over 20% market share), with over 20 million expected in 2025 [1]. As governments expand public charging infrastructure to meet soaring demand, centralized charging management faces limitations in scalability, cost, and resilience (e.g., single points of failure) [2], [3]. A promising alternative lies in decentralized charging control among EVs. It aims to allow EVs to manage their charging based on local conditions, user preference and grid/station needs without a central authority.

Transformers are theoretically reversal-invariant: their function class does not prefer left-to-right over right-to-left mappings. Yet empirical studies on natural language repeatedly report a "reversal curse," and recent work on temporal asymmetry in LLMs suggests that real-world corpora carry their own arrow of time. This leaves an unresolved question: do directional failures stem from linguistic statistics, or from the architecture itself? We cut through this ambiguity with a fully synthetic, entropy-controlled benchmark designed as a clean-room stress test for directional learning. Using random string mappings with tunable branching factor K, we construct forward tasks with zero conditional entropy and inverse tasks with analytically determined entropy floors. Excess loss above these floors reveals that even scratch-trained GPT-2 models exhibit a strong, reproducible directional optimization gap (e.g., 1.16 nats at K=5), far larger than that of an MLP trained on the same data. Pre-trained initializations shift optimization behavior but do not eliminate this gap, while LoRA encounters a sharp capacity wall on high-entropy inverse mappings. Together, these results isolate a minimal, semantics-free signature of directional friction intrinsic to causal Transformer training-one that persists even when linguistic priors, token frequencies, and corpus-level temporal asymmetries are removed. Our benchmark provides a controlled instrument for dissecting directional biases in modern sequence models and motivates deeper mechanistic study of why inversion remains fundamentally harder for Transformers.

A major field at the intersection of economics and computer science is the analysis of the efficiency of systems under strategic behavior.

Learning complex policies with Reinforcement Learning (RL) is often hindered by instability and slow convergence, a problem exacerbated by the difficulty of reward engineering. Imitation Learning (IL) from expert demonstrations bypasses this reliance on rewards. However, state-of-the-art IL methods, exemplified by Generative Adversarial Imitation Learning (GAIL)Ho et. al, suffer from severe sample inefficiency. This is a direct consequence of their foundational on-policy algorithms, such as TRPO Schulman et.al. In this work, we introduce an adversarial imitation learning algorithm that incorporates off-policy learning to improve sample efficiency. By combining an off-policy framework with auxiliary techniques specifically, double Q network based stabilization and value learning without reward function inference we demonstrate a reduction in the samples required to robustly match expert behavior.