AIConfPaper
← Search

Monica Sunkara

11 accepted papers

2025

Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection

Michelle Yuan, Khushbu Pahwa, Shuaichen Chang, Mustafa Devrim Kaba, MONICA SUNKARA, Jiarong Jiang +2
NeurIPS 2025poster

Designing effective agentic systems requires the seamless composition and integration of agents, tools, and models within dynamic and uncertain environments. Most existing methods rely on static, semantic retrieval approaches for tool or agent discovery. However, effective reuse and composition of e…

Cited by 0Source ↗Scholar ↗
2025

CONFETTI: Conversational Function-Calling Evaluation Through Turn-Level Interactions

Tamer Alkhouli, Katerina Margatina, James Gung, Raphael Shu, Claudia Zaghi, Monica Sunkara +1
ACL 2025long

We introduce Conversational Function-Calling Evaluation Through Turn-Level Interactions (CONFETTI), a conversational benchmark designed to evaluate the function-calling capabilities and response quality of large language models (LLMs). Current benchmarks lack comprehensive assessment of LLMs in comp…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

MemInsight: Autonomous Memory Augmentation for LLM Agents

Rana Salama, Jason Cai, Michelle Yuan, Anna Currey, Monica Sunkara, Yi Zhang +1
EMNLP 2025

Large language model (LLM) agents have evolved to intelligently process information, make decisions, and interact with users or tools. A key capability is the integration of long-term memory capabilities, enabling these agents to draw upon historical interactions and knowledge. However, the growing

Cited by 0Source ↗PDF ↗Scholar ↗
2025

SAMULE: Self-Learning Agents Enhanced by Multi-level Reflection

Yubin Ge, Salvatore Romeo, Jason Cai, Monica Sunkara, Yi Zhang
EMNLP 2025

Despite the rapid advancements in LLM agents, they still face the challenge of generating meaningful reflections due to inadequate error analysis and a reliance on rare successful trajectories, especially in complex tasks. In this work, we propose SAMULE, a new framework for self-learning agents pow

Cited by 0Source ↗PDF ↗Scholar ↗
2025

TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialogues

Yubin Ge, Salvatore Romeo, Jason Cai, Raphael Shu, Yassine Benajiba, Monica Sunkara +1
ACL 2025finding

Temporal reasoning in multi-session dialogues presents a significant challenge which has been under-studied in previous temporal reasoning benchmarks. To bridge this gap, we propose a new evaluation task for temporal reasoning in multi-session dialogues and introduce an approach to construct a new b…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

CERET: Cost-Effective Extrinsic Refinement for Text Generation

Jason Cai, Hang Su, Monica Sunkara, Igor Shalyminov, Saab Mansour
NAACL 2024long

Large Language Models (LLMs) are powerful models for generation tasks, but they may not generate good quality outputs in their first attempt. Apart from model fine-tuning, existing approaches to improve prediction accuracy and quality typically involve LLM self-improvement / self-reflection that inc…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2023

Mask the Bias: Improving Domain-Adaptive Generalization of CTC-Based ASR with Internal Language Model Estimation

Nilaksh Das, Monica Sunkara, Sravan Bodapati, Jinglun Cai, Devang Kulshreshtha, Jeff Farris +1
ICASSP 2023accepted

End-to-end ASR models trained on large amount of data tend to be implicitly biased towards language semantics of the training data. Internal language model estimation (ILME) has been proposed to mitigate this bias for autoregressive models such as attention-based encoder-decoder and RNN-T. Typically…

Cited by 0Source ↗Scholar ↗
2023

Masked Audio Text Encoders are Effective Multi-Modal Rescorers

Jinglun Cai, Monica Sunkara, Xilai Li, Anshu Bhatia, Xiao Pan, Sravan Bodapati
ACL 2023findings

Masked Language Models (MLMs) have proven to be effective for second-pass rescoring in Automatic Speech Recognition (ASR) systems. In this work, we propose Masked Audio Text Encoder (MATE), a multi-modal masked language model rescorer which incorporates acoustic representations into the input space…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2022

Listen, Know and Spell: Knowledge-Infused Subword Modeling for Improving ASR Performance of OOV Named Entities

Nilaksh Das, Duen Horng Chau, Monica Sunkara, Sravan Bodapati, Dhanush Bekal, Katrin Kirchhoff
ICASSP 2022accepted

Automatic speech recognition (ASR) is increasingly being used in specialized domains such as medical ASR and news transcription. Owing to the lack of high quality annotated speech data in such domains, off-the-shelf models are commonly employed by fine-tuning on domain-specific data. This poses a si…

Cited by 0Source ↗Scholar ↗