1 citations · 4 across the 41 of their papers we have counts for
46 papers
Self-Evolving Agents Can Repair Failures but Struggle to Generalize from Them
Weixiang Zhao, Yichen Zhang, Yanyan Zhao +5
Experience-driven self-evolution offers a promising path for large language model (LLM) agents to continually improve through interaction. Yet existing approaches often rely on suc…
HSD: Hybrid Hindsight Self-Distillation
Qiye Cai, Yichuan Ma, Peiji Li +7
Reinforcement learning with verifiable rewards (RLVR) provides reliable outcome supervision for language model reasoning, but scalar trajectory rewards offer limited guidance for t…
SL-BiLEM: Structured Learnable Behavior-in-the-Loop Epidemic Modeling for Forecasting and Policy Evaluation
Haochun Wang, Sendong Zhao, Jingbo Wang +3
Epidemic forecasting faces a fundamental challenge: human behavior dynamically responds to disease spread, creating feedback loops that induce distribution shifts at policy interve…
DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning
Yang He, Xiao Ding, Bibo Cai +5
Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during sequential tool invocation requ…
Easier to Judge than to Find: Predicting In-Context Learning Success for Demonstration Selection
Haochun Wang, Chaofen Yang, Jiatong Liu +5
In-context learning (ICL) is highly sensitive to which demonstrations appear in the prompt, but selecting them is expensive because the space of possible demonstration contexts and…
Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
Jiahe Guo, Xiangran Guo, Jiaxuan Chen +6
Multimodal large language models (MLLMs) often fail to transfer safety capabilities learned in the text modality to semantically equivalent non-text inputs, revealing a persistent…
Learning to Learn from Multimodal Experience
Xingyu Sui, Weixiang Zhao, Yongxin Tang +4
Experience-driven learning has emerged as a promising paradigm for enabling agents to improve from interaction trajectories by accumulating and reusing past experience. However, ex…
Rethinking Experience Utilization in Self-Evolving Language Model Agents
Weixiang Zhao, Yingshuo Wang, Yichen Zhang +6
Self-evolving agents improve by accumulating and reusing experience from past interactions. Existing work has largely focused on how experience is constructed, represented, and upd…
LSR-Ben: A Logical and Scientific Reasoning Benchmark for Evaluating Process Reward Models
Zhouhao Sun, Xuan Zhang, Xiao Ding +10
Currently, process reward models (PRMs) have exhibited remarkable potential for test-time scaling. Since large language models (LLMs) regularly generate flawed intermediate reasoni…
On Safety Risks in Experience-Driven Self-Evolving Agents
Weixiang Zhao, Yichen Zhang, Yingshuo Wang +8
Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduc…
x1: Learning to Think Adaptively Across Languages and Cultures
Yangfan Ye, Xiaocheng Feng, Xiachong Feng +8
Languages encode distinct abstractions and inductive priors, yet most large language models (LLMs) overlook this diversity by reasoning in a single dominant language. In this work,…
ConflictBench: Evaluating Human-AI Conflict via Interactive and Visually Grounded Environments
Weixiang Zhao, Haozhen Li, Yanyan Zhao +5
As large language models (LLMs) evolve into autonomous agents capable of acting in open-ended environments, ensuring behavioral alignment with human values becomes a critical safet…
AutoTool: Automatic Scaling of Tool-Use Capabilities in RL via Decoupled Entropy Constraints
Yirong Zeng, Xiao Ding, Yufei Liu +9
Tool use represents a critical capability for AI agents, with recent advances focusing on leveraging reinforcement learning (RL) to scale up the explicit reasoning process to achie…
Large Language Model Agents Are Not Always Faithful Self-Evolvers
Weixiang Zhao, Yingshuo Wang, Yichen Zhang +5
Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experie…
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration
Yang Zhao, Yangou Ouyang, Xiao Ding +8
While Hybrid Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become the standard paradigm for training LLM agents, effective mechanisms for data allocation…
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization
Yang Zhao, Hepeng Wang, Xiao Ding +8
Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), yet its efficacy is primarily confined to domains with ver…
Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch
Yirong Zeng, Xiao Ding, Yutai Hou +9
Training tool-augmented LLMs has emerged as a promising approach to enhancing language models' capabilities for complex tasks. The current supervised fine-tuning paradigm relies on…
Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement
Weixiang Zhao, Jiahe Guo, Yang Deng +7
Recent advancements in large reasoning models (LRMs) have significantly enhanced language models' capabilities in complex problem-solving by emulating human-like deliberative think…
Com: A Causal-Guided Benchmark for Exploring Complex Commonsense Reasoning in Large Language Models
Kai Xiong, Xiao Ding, Yixin Cao +7
Large language models (LLMs) have mastered abundant simple and explicit commonsense knowledge through pre-training, enabling them to achieve human-like performance in simple common…
CrossICL: Cross-Task In-Context Learning via Unsupervised Demonstration Transfer
Jinglong Gao, Xiao Ding, Lingxiao Zou +2
In-Context Learning (ICL) enhances the performance of large language models (LLMs) with demonstrations. However, obtaining these demonstrations primarily relies on manual effort. I…
ExpeTrans: LLMs Are Experiential Transfer Learners
Jinglong Gao, Xiao Ding, Lingxiao Zou +3
Recent studies provide large language models (LLMs) with textual task-solving experiences via prompts to improve their performance. However, previous methods rely on substantial hu…
Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning
Yang He, Xiao Ding, Bibo Cai +5
While reasoning-augmented large language models (RLLMs) significantly enhance complex task performance through extended reasoning chains, they inevitably introduce substantial unne…
Information Gain-Guided Causal Intervention for Autonomous Debiasing Large Language Models
Zhouhao Sun, Xiao Ding, Li Du +5
Despite significant progress, recent studies indicate that current large language models (LLMs) may still capture dataset biases and utilize them during inference, leading to the p…
MPO: Multilingual Safety Alignment via Reward Gap Optimization
Weixiang Zhao, Yulin Hu, Yang Deng +8
Large language models (LLMs) have become increasingly central to AI applications worldwide, necessitating robust multilingual safety alignment to ensure secure deployment across di…