32 citations · 63 across the 20 of their papers we have counts for
22 papers
Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents
Ido Levy, Asaf Yehudai, Segev Shlomov +2
An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested. Work on proactive agents mai…
Governance by Construction for Generalist Agents
Segev Shlomov, Iftach Shoham, Alon Oved +7
Enterprise agents are increasingly expected to operate autonomously across tools and interfaces, yet production deployments require governance by construction. Systems must specify…
Semantic Feature Analysis: Improving Agents Without Searching Over Rollouts
Roi Ben-Gigi, Yuval David, Fabiana Fournier +4
Ambiguity is an inherent property of natural-language agent specifications. When a system prompt leaves behaviour underdetermined, identical inputs follow divergent execution paths…
AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systems
Hadar Mulian, Sergey Zeltyn, Ido Levy +3
We introduce a comprehensive validation framework for LLM-based agentic systems that provides systematic diagnosis and improvement of reliability failures. The framework includes f…
TabAgent: Distilling LLM Agent Components into Cheap Classifiers
Ido Levy, Eilam Shapira, Yinon Goldshtein +5
Agentic systems, AI architectures that autonomously execute multi-step workflows to achieve complex goals, are often built using repeated large language model (LLM) calls for close…
Textual Planning with Explicit Latent Transitions
Eliezer Shlomi, Ido Levy, Eilam Shapira +6
Planning requires a transition model that predicts how each action changes the current state. When a large language model (LLM) plays this role, every next state is generated token…
General Agent Evaluation
Elron Bandel, Asaf Yehudai, Lilach Eden +12
General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes…
From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Production
Segev Shlomov, Alon Oved, Sami Marreed +9
Agents are rapidly advancing in automating digital work, but enterprises face a harder challenge: moving beyond prototypes to deployed systems that deliver measurable business valu…
Towards Enterprise-Ready Computer Using Generalist Agent
Sami Marreed, Alon Oved, Avi Yaeli +6
This paper presents our ongoing work toward developing an enterprise-ready Computer Using Generalist Agent (CUGA) system. Our research highlights the evolutionary nature of buildin…
ST-WebAgentBench: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents
Ido Levy, Ben Wiesel, Sami Marreed +4
Autonomous web agents solve complex browsing tasks, yet existing benchmarks measure only whether an agent finishes a task, ignoring whether it does so safely or in a way enterprise…
From Grounding to Planning: Benchmarking Bottlenecks in Web Agents
Segev Shlomov, Ben wiesel, Aviad Sela +3
General web-based agents are increasingly essential for interacting with complex web environments, yet their performance in real-world web applications remains poor, yielding extre…
IDA: Breaking Barriers in No-code UI Automation Through Large Language Models and Human-Centric Design
Segev Shlomov, Avi Yaeli, Sami Marreed +4
Business users dedicate significant amounts of time to repetitive tasks within enterprise digital platforms, highlighting a critical need for automation. Despite advancements in lo…
SNAP: Semantic Stories for Next Activity Prediction
Alon Oved, Segev Shlomov, Sergey Zeltyn +2
Predicting the next activity in an ongoing process is one of the most common classification tasks in the business process management (BPM) domain. It allows businesses to optimize…
Mimicking the Maestro: Exploring the Efficacy of a Virtual AI Teacher in Fine Motor Skill Acquisition
Hadar Mulian, Segev Shlomov, Lior Limonad +2
Motor skills, especially fine motor skills like handwriting, play an essential role in academic pursuits and everyday life. Traditional methods to teach these skills, although effe…
Ongoing Tracking of Engagement in Motor Learning
Segev Shlomov, Jonathan Muehlstein, Nitzan Guetta +1
Teaching motor skills such as playing music, handwriting, and driving, can greatly benefit from recently developed technologies such as wearable gloves for haptic feedback or robot…
Enhancing Trust in LLM-Based AI Automation Agents: New Considerations and Future Challenges
Sivan Schwartz, Avi Yaeli, Segev Shlomov
Trust in AI agents has been extensively studied in the literature, resulting in significant advancements in our understanding of this field. However, the rapid advancements in Larg…
Prescriptive Process Monitoring in Intelligent Process Automation with Chatbot Orchestration
Sergey Zeltyn, Segev Shlomov, Avi Yaeli +1
Business processes that involve AI-powered automation have been gaining importance and market share in recent years. These business processes combine the characteristics of classic…
Understanding the Properties of Generated Corpora
Naama Zwerdling, Segev Shlomov, Esther Goldbraich +6
Models for text generation have become focal for many research tasks and especially for the generation of sentence corpora. However, understanding the properties of an automaticall…
We've had this conversation before: A Novel Approach to Measuring Dialog Similarity
Ofer Lavi, Ella Rabinovich, Segev Shlomov +3
Dialog is a core building block of human natural language interactions. It contains multi-party utterances used to convey information from one party to another in a dynamic and evo…
Phase Transitions in Kyle's Model with Market Maker Profit Incentives
Charles-Albert Lehalle, Eyal Neuman, Segev Shlomov
We consider a stochastic game between three types of players: an inside trader, noise traders and a market maker. In a similar fashion to Kyle's model, we assume that the insider f…
Not Enough Data? Deep Learning to the Rescue!
Ateret Anaby-Tavor, Boaz Carmeli, Esther Goldbraich +5
Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a…
General Contact Process with Rapid Stirring
Segev Shlomov, Leonid Mytnik
We study the limiting behavior of an interacting particle system evolving on the lattice for . The model is known as the contact process with rapid stirring. The pr…