Papers with sub-agents
TDFlow: Agentic Workflows for Test Driven Development (2026.eacl-long)
Copied to clipboard
| Challenge: | TDFlow decomposes software engineering program repair into four components governed by sub-agents. |
| Approach: | They propose a test-driven agentic workflow that frames repository-scale software engineering as a testing task and decomposes it into four components governed by sub-agents. |
| Outcome: | The proposed workflow achieves 88.8% pass rate on SWE-Bench Lite and 94.3% on Swe-Bech Verified when provided with human-written tests. |
Structured Dialogue Policy with Graph Neural Networks (C18-1)
Copied to clipboard
| Challenge: | Recent advances focus on improving DRL-based dialogue policy optimization. |
| Approach: | They propose to design a graph neural network structure that is better suited for dialogue management. |
| Outcome: | The proposed approach outperforms state-of-the-art approaches in 18 tasks of the PyDial benchmark. |
Hierarchical Visual Agent: Managing Contexts in Joint Image-Text Space for Advanced Chart Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing MLLMs are strong at understanding single plots, but struggle with multi-step reasoning . Existing approaches to manage context in chart reasoning include text-based chain-of-thought prompting . |
| Approach: | They propose a hierarchical visual agent framework that iteratively constructs a working context in an image–text space. |
| Outcome: | The proposed framework improves on strong multimodal baselines. |