Papers by Zhixun Li

6 papers
Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards (2026.acl-long)

Copied to clipboard

Challenge: Large reasoning models are typically trained using reinforcement learning with verifiable reward (RLVR) positive and negative self-generated rollouts are used to update the model's policy . positive samples sharpen existing correct reasoning patterns, while negative samples encourage exploration of new reasoning paths.
Approach: They propose a method that allocates advantage signals to key tokens across different polarities.
Outcome: The proposed method improves the ability of large reasoning models to learn from their own generated rollouts.
AdaTooler-V: Adaptive Tool-Use for Images and Videos (2026.findings-acl)

Copied to clipboard

Challenge: Existing models exhibit blind tool-use reasoning patterns, which significantly increases inference overhead and degrades model performance.
Approach: They propose an MLLM that performs adaptive tool-use by determining whether a visual problem truly requires tools.
Outcome: The proposed model outperforms existing methods in visual reasoning tasks.
Semantics-Aware Dual Graph Convolutional Networks for Argument Pair Extraction (2024.lrec-main)

Copied to clipboard

Challenge: Argument pair extraction (APE) aims to extract interactive argument pairs from two separate passages.
Approach: They propose to tackle the lexical and semantic relevance of arguments with a pre-trained Rouge-guided Transformer (ROT) by using a word graph and a gating mechanism to fuse two graphs.
Outcome: The proposed approach achieves state-of-the-art on F1 score and significantly improves on existing best alternative.
RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task Evaluation (2026.acl-long)

Copied to clipboard

Challenge: Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains, but their ability to replicate complex, multi-panel visualizations remains largely unassessed.
Approach: They propose a large-scale benchmark to evaluate chart generation from large- scale raw data and assess iterative code refinement in a multi-turn conversational setting.
Outcome: The new benchmark evaluates 14 leading VLMs on real-world data and shows they struggle with complex plot structures and authentic data.
ATLAS: Agent Tuning via Learning Critical Steps (2025.findings-acl)

Copied to clipboard

Challenge: Existing agent tuning approaches employ supervised finetuning on entire expert trajectories, but behavior-cloning of full traitories introduces expert bias and weakens generalization to states not covered by the expert data.
Approach: They propose a method that finetunes LLMs on critical steps in expert trajectories and identifies and finetuns them on these steps with reduced costs.
Outcome: The proposed method outperforms existing methods and open-source LLM agents on only 30% critical steps in extensive experiments.
Exploring Reasoning Reward Model for Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for agentic reinforcement learning rely on sparse outcome-based reward for training, leading to suboptimal results.
Approach: They propose an agent-based reward model that produces structured feedback for agentic trajectories, including an explicit reasoning trace and a focused critique.
Outcome: The proposed model produces structured feedback for agentic trajectories including an explicit reasoning trace, a focused critique, and an overall score that evaluates process performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations