activity
20242026
most citedMORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning

12 citations · 16 across the 10 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents

Boyang Yang, Zhenhao Li, Ziyao Yang +4

Agents built on large language models (LLMs) build and run software through tool calls. A call reaches its program through several hops, and any hop can change the call without not…