10 papers
Long-Horizon Textual World Modeling through Structured Reasoning
Fangxin Wang, Xiang Gao, Yuguang Yao +3
World models must predict how an environment evolves under sequences of actions, enabling agents to compare possible futures and reason about counterfactual actions before acting.…
Observational Policy Ranking for SMB Financial Guidance from Multi-Action Accounting Logs
Shrutendra Harsola, Vignesh Subrahmaniam, Vikas Raturi +7
Small and medium-sized businesses need timely financial guidance, yet historical accounting logs record self-selected and often co-occurring business changes rather than randomized…
Textual Belief States for World Models: Identifiable Representation Learning Under Strict Mediation
Xiang Gao, Kaiwen Dong, Yuguang Yao +2
World models in partially observed environments rely on latent representations that summarize interaction history, but in many modern LLM-based architectures predictive performance…
Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval
Padmaja Jonnalagedda, Yuguang Yao, Xiang Gao +2
Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent schemas and formats…
When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories
Avinash Baidya, Xinran Liang, Ruocheng Guo +2
Early failure alerting requires deciding, while a dialog or agent trajectory is still unfolding, whether to flag it as likely to fail. This is challenging because supervision is ty…
REMem: Reasoning with Episodic Memory in Language Agent
Yiheng Shu, Saisri Padmaja Jonnalagedda, Xiang Gao +5
Humans excel at remembering concrete experiences along spatiotemporal contexts and performing reasoning across those events, i.e., the capacity for episodic memory. In contrast, me…
Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use
Ruocheng Guo, Kaiwen Dong, Xiang Gao +1
While most efforts to improve LLM-based tool-using agents focus on the agent itself - through larger models, better prompting, or fine-tuning - agent performance increasingly plate…
RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning
Xiang Gao, Yuguang Yao, Qi Zhang +5
Large language models (LLMs) often struggle to use tools reliably in domain-specific settings, where APIs may be idiosyncratic, under-documented, or tailored to private workflows.…
The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs
Avinash Baidya, Kamalika Das, Xiang Gao
Large Language Model (LLM)-based agents have significantly impacted Task-Oriented Dialog Systems (TODS) but continue to face notable performance challenges, especially in zero-shot…
Transaction Categorization with Relational Deep Learning in QuickBooks
Kaiwen Dong, Padmaja Jonnalagedda, Xiang Gao +5
Automatic transaction categorization is crucial for enhancing the customer experience in QuickBooks by providing accurate accounting and bookkeeping. The distinct challenges in thi…