57 citations · 67 across the 10 of their papers we have counts for
7 papers · 1 filter
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…