11 papers
Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
Vardhan Dongre, Dilek Hakkani-Tür
Effective collaboration between embodied agents requires more than acting in a shared environment; it demands communication grounded in each agent's evolving understanding of the w…
Trajectory-Level Redirection Attacks on Vision-Language-Action Models
Gokul Puthumanaillam, Vardhan Dongre, Pranay Thangeda +3
Vision-language-action (VLA) policies bring natural language into closed-loop robot control, enabling robots to execute manipulation tasks directly from text instructions. The same…
When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
Vardhan Dongre, Joseph Hsieh, Viet Dac Lai +3
Large language models can follow complex instructions in a single turn, yet over long multi-turn interactions they often lose the thread of instructions, persona, and rules. This d…
MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations
Vardhan Dongre, Chi Gui, Shubham Garg +4
We introduce MIRAGE, a new benchmark for multimodal expert-level reasoning and decision-making in consultative interaction settings. Designed for the agriculture domain, MIRAGE cap…
Plan Verification for LLM-Based Embodied Task Completion Agents
Ananth Hariharan, Vardhan Dongre, Dilek Hakkani-Tür +1
Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors…
Drift No More? Context Equilibria in Multi-Turn LLM Interactions
Vardhan Dongre, Ryan A. Rossi, Viet Dac Lai +3
Large Language Models (LLMs) excel at single-turn tasks such as instruction following and summarization, yet real-world deployments require sustained multi-turn interactions where…