Papers by Zhenfei Yin

8 papers
From Word to World: Can Large Language Models be Implicit Text-based World Models? (2026.acl-long)

Copied to clipboard

Challenge: Agentic learning increasingly hinges on interaction, yet real-world experience is expensive, limited, and often irreversible at inference time.
Approach: They propose a framework that reframes language modeling as next-state prediction under interaction.
Outcome: The proposed framework evaluates world models in text-based environments . it shows that sufficiently trained models capture coherent environment dynamics .
SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing security benchmarks only cover user-level prompts and environmental threats . however, these models are vulnerable to pop-up attacks and prompt injections .
Approach: They propose a security benchmark that covers a set of six attack vectors that span both user-level and environment-level manipulations.
Outcome: The proposed security benchmarks cover a set of six real-world web environments with 2,970 adversarial trajectories and a multi-layered evaluation protocol dissecting agent failures across internal reasoning, behavioral execution, and task outcomes.
Rethinking the Role of Entropy in Optimizing Tool-Use Behaviors for Large Language Model Agents (2026.acl-long)

Copied to clipboard

Challenge: Large language models excel in mathematical reasoning and multi-hop question answering tasks, but in long trajectories, agents often invoke tools excessively or inappropriately, increasing computation cost and derailing the reasoning process.
Approach: They propose to use entropy reduction as a supervisory signal to reduce tool calls . they propose to design two reward strategies to address the needs of optimizing tool-use behavior.
Outcome: The proposed reward strategies reduce tool calls by 72.07% and improve performance by 22.27%.
Towards Tracing Trustworthiness Dynamics: Revisiting Pre-training Period of Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Existing studies focus on pre-trained LLMs to better understand and improve their trustworthiness.
Approach: They apply linear probing to LLMs to explore five key dimensions of trustworthiness: reliability, privacy, toxicity, fairness, and robustness.
Outcome: The proposed model can distinguish concepts in each trustworthiness dimension, suggesting that it can be trained in early pre-training.
Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System (2025.acl-long)

Copied to clipboard

Challenge: Recent AI methods have shown promise in tasks such as hypothesis generation and experimental design, but they fail to replicate the collaborative nature of real-world scientific practices.
Approach: They propose a virtual scientific system that mimics the collaborative nature of scientific research by organizing a team of agents to generate, evaluate, and refine research ideas.
Outcome: The proposed system outperforms the state-of-the-art method in producing new scientific ideas and offers valuable insights to guide future research.
ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks (2025.emnlp-main)

Copied to clipboard

Challenge: Multi-agent systems (MAS) are limited by poor flexibility and scalability, with underdeveloped optimization strategies.
Approach: They propose a task graph generation and a reward-driven two-stage agent selection process to integrate multi-agent systems to improve their reasoning capabilities.
Outcome: The proposed model outperforms existing methods on Math-MAS and SciBench-MAS SciBech, while other methods completely fail.
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning (2026.acl-long)

Copied to clipboard

Challenge: elucidating scaling laws for large language models (LLMs) during pre-training remains unexplored.
Approach: They characterize how model scale, data, and compute interact during pre-training . they find that large models consistently demonstrate superior compute and data efficiency .
Outcome: The proposed scaling laws offer practical guidance for scaling reasoning capabilities through reinforcement learning post-training.
Behavioral Consistency Validation for LLM Agents: An Analysis of Trading-Style Switching through Stock-Market Simulation (2026.findings-acl)

Copied to clipboard

Challenge: Recent studies have applied Large Language Models (LLMs) as agents in financial stock market simulations to test if micro-level behaviors aggregate into macro-level phenomena.
Approach: They propose four alignment metrics and use Mann–Whitney U tests to compare agents’ style-switching behavior with financial theory.
Outcome: The proposed model is only partially consistent with financial theory.

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