Tianyang Liu
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8CocoaBench: Evaluating Unified Digital Agents in the Wild
arXiv 2026
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective
arXiv 2025
BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution
arXiv 2025
Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs
arXiv 2025
Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models
arXiv 2024
Rethinking Tabular Data Understanding with Large Language Models
arXiv 2023
ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings
toolkengpt-augmenting-frozen-language-models
RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
arXiv 2023
Affiliations
Frequent co-authors
10from 8 papers