57 citations · 67 across the 10 of their papers we have counts for
14 papers
RLPE: Teaching LLMs to Prompt with Reinforcement Learning
Rahul Singhal, Karime Maamari, Pradyumna Tambwekar
Prompting is a widely used method for adapting general-purpose LLMs to domain-specific tasks. Effective prompts can be tedious to create manually, so prompt writing is increasingly…
AgentMemGate: Addressing Speculation Contamination in Conversational Assistant Memory
Chirag Sharma, Benjamin Fowlersmith, Karime Maamari
Conversational AI assistants with long-term memory extract facts from user messages into a store consulted in later conversations. A stated plan can enter that store as fact: a use…
HARDEN: Constrained Evolutionary Search for Harder, Answer-Preserving Evaluation Cases
Aditya Kumaran, Rahul Singhal, Karime Maamari +2
Language models are often evaluated on curated benchmarks that underrepresent the complexity of enterprise deployments. We introduce HARDEN, a constrained evolutionary search metho…
Proxifield: Decentralized Multi-Agent Communication through Semantic Proximity
Pradyumna Tambwekar, Yenchia Feng, Deep Patel +1
As LLM capabilities have expanded, multi-agent communication has emerged as an increasingly active area of research. Prevailing protocols often adopt rigid structures that introduc…
Environment Maps: Structured Environmental Representations for Long-Horizon Agents
Yenchia Feng, Chirag Sharma, Karime Maamari
Although large language models (LLMs) have advanced rapidly, robust automation of complex software workflows remains an open problem. In long-horizon settings, agents frequently su…
PrefPO: Pairwise Preference Prompt Optimization
Rahul Singhal, Pradyumna Tambwekar, Karime Maamari
Prompt engineering is effective but labor-intensive, motivating automated optimization methods. Existing methods typically require labeled datasets, which are often unavailable, an…
Lattice: Generative Guardrails for Conversational Agents
Emily Broadhurst, Tawab Safi, Joseph Edell +2
Conversational AI systems require guardrails to prevent harmful outputs, yet existing approaches use static rules that cannot adapt to new threats or deployment contexts. We introd…
How Many Instructions Can LLMs Follow at Once?
Daniel Jaroslawicz, Brendan Whiting, Parth Shah +1
Production-grade LLM systems require robust adherence to dozens or even hundreds of instructions simultaneously. However, the instruction-following capabilities of LLMs at high ins…
GenEdit: Compounding Operators and Continuous Improvement to Tackle Text-to-SQL in the Enterprise
Karime Maamari, Connor Landy, Amine Mhedhbi
Recent advancements in Text-to-SQL, driven by large language models, are democratizing data access. Despite these advancements, enterprise deployments remain challenging due to the…
The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models
Karime Maamari, Fadhil Abubaker, Daniel Jaroslawicz +1
Schema linking is a crucial step in Text-to-SQL pipelines. Its goal is to retrieve the relevant tables and columns of a target database for a user's query while disregarding irrele…
End-to-end Text-to-SQL Generation within an Analytics Insight Engine
Karime Maamari, Amine Mhedhbi
Recent advancements in Text-to-SQL have pushed database management systems towards greater democratization of data access. Today's language models are at the core of these advancem…
Effects of boosting on extragalactic components: methods and statistical studies
William R. Coulton, Sydney Feldman, Karime Maamari +3
In this work we examine the impact of our motion with respect to the CMB rest frame on statistics of CMB maps by examining the one-, two-, three- and four- point statistics of simu…
Bounds on velocity-dependent dark matter-proton scattering from Milky Way satellite abundance
Karime Maamari, Vera Gluscevic, Kimberly K. Boddy +2
We use the latest measurements of the Milky Way satellite population from the Dark Energy Survey and Pan-STARRS1 to infer the most stringent astrophysical bound to date on velocity…
Validating Planck SZ2 Clusters with Optical Counterparts
Panchajanya Banerjee, Elena Pierpaoli, Nareg Mirzatuny +2
We perform an extensive analysis of optical counterparts of Planck PSZ2 clusters, considering matches with three recent catalogs built from SDSS data: AMF DR9, redMaPPer (v6.3) and…