5 papers
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Changdae Oh, Wendi Li, Seongheon Park +3
Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-horizon interactions, irrever…
Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning
Fatema Siddika, Md Anwar Hossen, Tanwi Mallick +1
Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previ…
MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding
Siddeshwar Raghavan, Tanwi Mallick
We present MOSAIC, a multi-agent Large Language Model (LLM) framework for solving challenging scientific coding tasks. Unlike general-purpose coding, scientific workflows require a…
Split-on-Share: Mixture of Sparse Experts for Task-Agnostic Continual Learning
Fatema Siddika, Md Anwar Hossen, Tanwi Mallick +1
Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previ…
LUMINA: Detecting Hallucinations in RAG System with Context-Knowledge Signals
Samuel Yeh, Sharon Li, Tanwi Mallick
Retrieval-Augmented Generation (RAG) aims to mitigate hallucinations in large language models (LLMs) by grounding responses in retrieved documents. Yet, RAG-based LLMs still halluc…