5 papers
Hypergraph Enterprise Agentic Reasoner over Heterogeneous Business Systems
Ling Wang, Xin Liu, Songnan Liu +8
Applying Large Language Models (LLMs) to heterogeneous enterprise systems is hindered by hallucinations and failures in multi-hop, n-ary reasoning. Existing paradigms (e.g., GraphR…
Automating Android Build Repair: Bridging the Reasoning-Execution Gap in LLM Agents with Domain-Specific Tools
Ha Min Son, Huan Ren, Xin Liu +1
Android is the largest mobile platform, yet automatically building applications remains a practical challenge. While Large Language Models (LLMs) show promise for code repair, thei…
RADAR: Benchmarking Language Models on Imperfect Tabular Data
Ken Gu, Zhihan Zhang, Kate Lin +18
Language models (LMs) are increasingly being deployed to perform autonomous data analyses. However, their data awareness -- the ability to recognize, reason over, and appropriately…
PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solving
Mihir Parmar, Palash Goyal, Xin Liu +5
Recently, decomposing complex problems into simple subtasks--a crucial part of human-like natural planning--to solve the given problem has significantly boosted the performance of…
PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
Mihir Parmar, Xin Liu, Palash Goyal +11
Recent agent frameworks and inference-time algorithms often struggle with complex planning problems due to limitations in verifying generated plans or reasoning and varying complex…