Optimizing Agentic Workflows using Meta-tools

Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks. However, agentic workflows often require many iterative reasoning steps and tool invocations, leading to significant operational expense, end-to-end latency and failures due to hallucinations. This work introduces Agent Workflow Optimization (AWO), a framework that identifies and optimizes redundant tool execution patterns to improve the efficiency and robustness of agentic workflows. AWO analyzes existing workflow traces to discover recurring sequences of tool calls and transforms them into meta-tools, which are deterministic, composite tools that bundle multiple agent actions into a single invocation. Meta-tools bypass unnecessary intermediate LLM reasoning steps and reduce operational cost while also shortening execution paths, leading to fewer failures. Experiments on two agentic AI benchmarks show that AWO reduces the number of LLM calls up to 11.9% while also increasing the task success rate by up to 4.2 percent points.

Effective LoRA Adapter Routing using Task Representations

Low-rank adaptation (LoRA) enables parameter efficient specialization of large language models (LLMs) through modular adapters, resulting in rapidly growing public adapter pools spanning diverse tasks. Effectively using these adapters requires routing: selecting and composing the appropriate adapters for a query. We introduce LORAUTER, a novel routing framework that selects and composes LoRA adapters using task representations rather than adapter characteristics. Unlike existing approaches that map queries directly to adapters, LORAUTER routes queries via task embeddings derived from small validation sets and does not require adapter training data. By operating at the task level, LORAUTER achieves efficient routing that scales with the number of tasks rather than the number of adapters. Experiments across multiple tasks show that LORAUTER consistently outperforms baseline routing approaches, matching Oracle performance (101.2%) when task-aligned adapters exist and achieving state-of-the-art results on unseen tasks (+5.2 points). We further demonstrate the robustness of LORAUTER to very large, noisy adapter pools by scaling it to over 1500 adapters.

Navigating the Accuracy-Size Trade-Off with Flexible Model Merging

Model merging has emerged as an efficient method to combine multiple single-task fine-tuned models. The merged model can enjoy multi-task capabilities without expensive training. While promising, merging into a single model often suffers from an accuracy gap with respect to individual fine-tuned models. On the other hand, deploying all individual fine-tuned models incurs high costs. We propose FlexMerge, a novel data-free model merging framework to flexibly generate merged models of varying sizes, spanning the spectrum from a single merged model to retaining all individual fine-tuned models. FlexMerge treats fine-tuned models as collections of sequential blocks and progressively merges them using any existing data-free merging method, halting at a desired size. We systematically explore the accuracy-size trade-off exhibited by different merging algorithms in combination with FlexMerge. Extensive experiments on vision and NLP benchmarks, with up to 30 tasks, reveal that even modestly larger merged models can provide substantial accuracy improvements over a single model. By offering fine-grained control over fused model size, FlexMerge provides a flexible, data-free, and high-performance solution for diverse deployment scenarios.

Collaborative Agentic AI Needs Interoperability Across Ecosystems

Collaborative agentic AI is projected to transform entire industries by enabling AI-powered agents to autonomously perceive, plan, and act within digital environments. Yet, current solutions in this field are all built in isolation, and we are rapidly heading toward a landscape of fragmented, incompatible ecosystems. In this position paper, we argue that interoperability, achieved by the adoption of minimal standards, is essential to ensure open, secure, web-scale, and widely-adopted agentic ecosystems. To this end, we devise a minimal architectural foundation for collaborative agentic AI, named Web of Agents, which is composed of four components: agent-to-agent messaging, interaction interoperability, state management, and agent discovery. Web of Agents adopts existing standards and reuses existing infrastructure where possible. With Web of Agents, we take the first but critical step toward interoperable agentic systems and offer a pragmatic path forward before ecosystem fragmentation becomes the norm.

Robust ML Auditing using Prior Knowledge

The rapid adoption of ML decision-making systems across products and services has led to a set of regulations on how such systems should behave and be built. Among all the technical challenges to enforcing these regulations, one crucial, yet under-explored problem is the risk of manipulation while these systems are being audited for fairness. This manipulation occurs when a platform deliberately alters its answers to a regulator to pass an audit without modifying its answers to other users. In this paper, we introduce a novel approach to manipulation-proof auditing by taking into account the auditor's prior knowledge of the task solved by the platform. We first demonstrate that regulators must not rely on public priors (e.g. a public dataset), as platforms could easily fool the auditor in such cases. We then formally establish the conditions under which an auditor can prevent audit manipulations using prior knowledge about the ground truth. Finally, our experiments with two standard datasets exemplify the maximum level of unfairness a platform can hide before being detected as malicious. Our formalization and generalization of manipulation-proof auditing with a prior opens up new research directions for more robust fairness audits.

Accelerating MoE Model Inference with Expert Sharding

Mixture of experts (MoE) models achieve state-of-the-art results in language modeling but suffer from inefficient hardware utilization due to imbalanced token routing and communication overhead. While prior work has focused on optimizing MoE training and decoder architectures, inference for encoder-based MoE models in a multi-GPU with expert parallelism setting remains underexplored. We introduce MoEShard, an inference system that achieves perfect load balancing through tensor sharding of MoE experts. Unlike existing approaches that rely on heuristic capacity factors or drop tokens, MoEShard evenly distributes computation across GPUs and ensures full token retention, maximizing utilization regardless of routing skewness. We achieve this through a strategic row- and column-wise decomposition of expert matrices. This reduces idle time and avoids bottlenecks caused by imbalanced expert assignments. Furthermore, MoEShard minimizes kernel launches by fusing decomposed expert computations, significantly improving throughput. We evaluate MoEShard against DeepSpeed on encoder-based architectures, demonstrating speedups of up to 6.4$\times$ in time to first token (TTFT). Our results show that tensor sharding, when properly applied to experts, is a viable and effective strategy for efficient MoE inference.

Leveraging Approximate Caching for Faster Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) enhances the reliability of large language model (LLM) answers by integrating external knowledge. However, RAG increases the end-to-end inference time since looking for relevant documents from large vector databases is computationally expensive. To address this, we introduce Proximity, an approximate key-value cache that optimizes the RAG workflow by leveraging similarities in user queries. Instead of treating each query independently, Proximity reuses previously retrieved documents when similar queries appear, reducing reliance on expensive vector database lookups. We evaluate Proximity on the MMLU and MedRAG benchmarks, demonstrating that it significantly improves retrieval efficiency while maintaining response accuracy. Proximity reduces retrieval latency by up to 59% while maintaining accuracy and lowers the computational burden on the vector database. We also experiment with different similarity thresholds and quantify the trade-off between speed and recall. Our work shows that approximate caching is a viable and effective strategy for optimizing RAG-based systems.

Efficient Federated Search for Retrieval-Augmented Generation

Large language models (LLMs) have demonstrated remarkable capabilities across various domains but remain susceptible to hallucinations and inconsistencies, limiting their reliability. Retrieval-augmented generation (RAG) mitigates these issues by grounding model responses in external knowledge sources. Existing RAG workflows often leverage a single vector database, which is impractical in the common setting where information is distributed across multiple repositories. We introduce RAGRoute, a novel mechanism for federated RAG search. RAGRoute dynamically selects relevant data sources at query time using a lightweight neural network classifier. By not querying every data source, this approach significantly reduces query overhead, improves retrieval efficiency, and minimizes the retrieval of irrelevant information. We evaluate RAGRoute using the MIRAGE and MMLU benchmarks and demonstrate its effectiveness in retrieving relevant documents while reducing the number of queries. RAGRoute reduces the total number of queries up to 77.5% and communication volume up to 76.2%.

Revisiting Ensembling in One-Shot Federated Learning

Federated learning (FL) is an appealing approach to training machine learning models without sharing raw data. However, standard FL algorithms are iterative and thus induce a significant communication cost. One-shot federated learning (OFL) trades the iterative exchange of models between clients and the server with a single round of communication, thereby saving substantially on communication costs. Not surprisingly, OFL exhibits a performance gap in terms of accuracy with respect to FL, especially under high data heterogeneity. We introduce FENS, a novel federated ensembling scheme that approaches the accuracy of FL with the communication efficiency of OFL. Learning in FENS proceeds in two phases: first, clients train models locally and send them to the server, similar to OFL; second, clients collaboratively train a lightweight prediction aggregator model using FL. We showcase the effectiveness of FENS through exhaustive experiments spanning several datasets and heterogeneity levels. In the particular case of heterogeneously distributed CIFAR-10 dataset, FENS achieves up to a 26.9% higher accuracy over state-of-the-art (SOTA) OFL, being only 3.1% lower than FL. At the same time, FENS incurs at most 4.3x more communication than OFL, whereas FL is at least 10.9x more communication-intensive than FENS.

Boosting Asynchronous Decentralized Learning with Model Fragmentation

Decentralized learning (DL) is an emerging technique that allows nodes on the web to collaboratively train machine learning models without sharing raw data. Dealing with stragglers, i.e., nodes with slower compute or communication than others, is a key challenge in DL. We present DivShare, a novel asynchronous DL algorithm that achieves fast model convergence in the presence of communication stragglers. DivShare achieves this by having nodes fragment their models into parameter subsets and send, in parallel to computation, each subset to a random sample of other nodes instead of sequentially exchanging full models. The transfer of smaller fragments allows more efficient usage of the collective bandwidth and enables nodes with slow network links to quickly contribute with at least some of their model parameters. By theoretically proving the convergence of DivShare, we provide, to the best of our knowledge, the first formal proof of convergence for a DL algorithm that accounts for the effects of asynchronous communication with delays. We experimentally evaluate DivShare against two state-of-the-art DL baselines, AD-PSGD and Swift, and with two standard datasets, CIFAR-10 and MovieLens. We find that DivShare with communication stragglers lowers time-to-accuracy by up to 3.9x compared to AD-PSGD on the CIFAR-10 dataset. Compared to baselines, DivShare also achieves up to 19.4% better accuracy and 9.5% lower test loss on the CIFAR-10 and MovieLens datasets, respectively.