9 citations · 17 across the 18 of their papers we have counts for
18 papers
ClawGym II: Exploring Black-Box RL on Agent Harness
Huatong Song, Fei Bai, Ming Yang +17
Agent harnesses have substantially improved performance on long-horizon tasks by coordinating agent interactions with the environment. However, reinforcement learning through compl…
ClawGym: A Scalable Framework for Building Effective Claw Agents
Fei Bai, Huatong Song, Shuang Sun +11
Claw-style environments support multi-step workflows over local files, tools, and persistent workspace states. However, scalable development around these environments remains const…
BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
Guoxin Chen, Fanzhe Meng, Jiale Zhao +12
Current code-agent benchmarks primarily evaluate localized issue resolution within a single target repository, leaving under-tested many software engineering tasks that require ext…
SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
Huatong Song, Lisheng Huang, Shuang Sun +11
In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master system…
HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders
Kun Yuan, Junyu Bi, Daixuan Cheng +5
Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory…
Generative Pseudo-Labeling for Pre-Ranking with LLMs
Junyu Bi, Xinting Niu, Daixuan Cheng +4
Pre-ranking is a critical stage in industrial recommendation systems, tasked with efficiently scoring thousands of recalled items for downstream ranking. A key challenge is the tra…
Computer Environments Elicit General Agentic Intelligence in LLMs
Daixuan Cheng, Shaohan Huang, Yuxian Gu +6
Agentic intelligence in large language models (LLMs) requires not only model intrinsic capabilities but also interactions with external environments. Equipping LLMs with computers…
How Efficient Are Diffusion Language Models? A Critical Examination of Efficiency Evaluation Practices
Han Peng, Peiyu Liu, Zican Dong +5
Diffusion language models (DLMs) have emerged as a promising alternative to the long-dominant autoregressive (AR) paradigm, offering a parallelable decoding process that could yiel…
FlowRL: Matching Reward Distributions for LLM Reasoning
Xuekai Zhu, Daixuan Cheng, Dinghuai Zhang +20
We propose FlowRL: matching the full reward distribution via flow balancing instead of maximizing rewards in large language model (LLM) reinforcement learning (RL). Recent advanced…
From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR
Jia Deng, Jie Chen, Zhipeng Chen +7
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). Unlike traditiona…
Reasoning with Exploration: An Entropy Perspective
Daixuan Cheng, Shaohan Huang, Xuekai Zhu +4
Balancing exploration and exploitation is a central goal in reinforcement learning (RL). Despite recent advances in enhancing large language model (LLM) reasoning, most methods lea…
An Empirical Study on Eliciting and Improving R1-like Reasoning Models
Zhipeng Chen, Yingqian Min, Beichen Zhang +10
In this report, we present the third technical report on the development of slow-thinking models as part of the STILL project. As the technical pathway becomes clearer, scaling RL…
How to Synthesize Text Data without Model Collapse?
Xuekai Zhu, Daixuan Cheng, Hengli Li +7
Model collapse in synthetic data indicates that iterative training on self-generated data leads to a gradual decline in performance. With the proliferation of AI models, synthetic…
On Domain-Adaptive Post-Training for Multimodal Large Language Models
Daixuan Cheng, Shaohan Huang, Ziyu Zhu +5
Adapting general multimodal large language models (MLLMs) to specific domains, such as scientific and industrial fields, is highly significant in promoting their practical applicat…
Instruction Pre-Training: Language Models are Supervised Multitask Learners
Daixuan Cheng, Yuxian Gu, Shaohan Huang +3
Unsupervised multitask pre-training has been the critical method behind the recent success of language models (LMs). However, supervised multitask learning still holds significant…
Adapting Large Language Models to Domains via Reading Comprehension
Daixuan Cheng, Shaohan Huang, Furu Wei
We explore how continued pre-training on domain-specific corpora influences large language models, revealing that training on the raw corpora endows the model with domain knowledge…
How Does Diffusion Influence Pretrained Language Models on Out-of-Distribution Data?
Huazheng Wang, Daixuan Cheng, Haifeng Sun +5
Transformer-based pretrained language models (PLMs) have achieved great success in modern NLP. An important advantage of PLMs is good out-of-distribution (OOD) robustness. Recently…
UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation
Daixuan Cheng, Shaohan Huang, Junyu Bi +7
Large Language Models (LLMs) are popular for their impressive abilities, but the need for model-specific fine-tuning or task-specific prompt engineering can hinder their generaliza…