24 citations · 54 across the 30 of their papers we have counts for
33 papers
LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models
Yida Cai, Xin Dai, Bingxiang He +5
Legal language models require reward signals that capture not only answer correctness but also the multidimensional quality of legal responses. Existing reward methods, however, of…
Diffusion Reward Models
Xiangyang Wang, Bingxiang He, Zeyuan Liu +14
Reward models underpin the alignment of large language models, yet the dominant designs reduce each prompt--response pair to a point estimate or to a distribution from a fixed para…
StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?
Yinghao Chen, Zixi Chen, Bingxiang He +7
Humans need to study only a handful of well-written textbooks to master a discipline and attempt its hardest problems. We argue that an ideal self-evolution method should share the…
On-policy Distillation with Verifiable Reward
Wenze Lin, Jiale Zhao, Xitai Jiang +5
Reinforcement Learning with Verifiable Rewards (RLVR) and on-policy distillation (OPD) have become two widely adopted paradigms for post-training large language models. However, RL…
SWE Refactor Bench: Can Coding Agents Complete a Long-Horizon, Whole-Repository Stack Migration?
Deyao Hong, Yizhe Chi, Wenyi Li +7
Modern software systems accumulate technical debt over decades of development, which makes migration expensive and largely manual. As coding agents become increasingly capable at b…
AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement
Yizhe Chi, Wenyi Li, Deyao Hong +7
Recursive self-improvement (RSI) asks whether an AI system can improve the process that produces AI systems, so that the next system inherits the improvement. That process is the t…
Open-MOPD: Diagnosing and Fixing Capability Imbalance in Multi-Teacher On-Policy Distillation
Huan-ang Gao, Haohan Chi, Yong Yan +7
Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) experts into a single generalist s…
PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments
Yuhao Zhan, Bingxiang He, Zecong Tang +1
Self-evolving agents improve future behavior from interaction experience, yet existing evaluations typically optimize under fixed execution conditions and do not test recovery afte…
Weak-to-Strong Generalization via Direct On-Policy Distillation
Shiyuan Feng, Huan-ang Gao, Haohan Chi +7
Reinforcement learning with verifiable rewards (RLVR) is a powerful recipe for improving language-model reasoning, but it is expensive to repeat on every new strong model because t…
NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?
Yuru Wang, Lejun Cheng, Yuxin Zuo +14
We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether AI coding agents can move b…
Scalable Behaviour Cloning on Browser Using via Skill Distillation
Kaisen Yang, Zheng Jiang, Yuzhao Peng +11
Internet users collectively perform an enormous range of skilled work through web browsers, from software development and document editing to search, forms, and enterprise workflow…
Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
Zewen Liu, Zhan Shi, Yisi Sang +7
Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infrastructure from execution feedba…
A-Evolve-Training: Autonomous Post-Training of a 30B Model
Zhan Shi, Bing He, Yisi Sang +2
Post-training a frontier model is normally weeks of human work: proposing data and recipe changes, launching runs, reading evals, deciding what to keep. We report an autonomous sys…
CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing
Cheng Qian, Hyeonjeong Ha, Jiayu Liu +10
Recent advances in large language models have led to strong performance on reasoning and environment-interaction tasks, yet their ability for creative problem-solving remains under…
Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization
Yizhe Chi, Deyao Hong, Dapeng Jiang +18
Current LLM agent benchmarks, which predominantly focus on binary pass/fail tasks such as code generation or search-based question answering, often neglect the value of real-world…
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
Yaxuan Li, Yuxin Zuo, Bingxiang He +8
On-policy distillation (OPD) has become a core technique in the post-training of large language models, yet its training dynamics remain poorly understood. This paper provides a sy…
How Far Can Unsupervised RLVR Scale LLM Training?
Bingxiang He, Yuxin Zuo, Zeyuan Liu +18
Unsupervised reinforcement learning with verifiable rewards (URLVR) offers a pathway to scale LLM training beyond the supervision bottleneck by deriving rewards without ground trut…
How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
Yingqian Cui, Zhenwei Dai, Bing He +7
Latent reasoning has been recently proposed as a reasoning paradigm and performs multi-step reasoning through generating steps in the latent space instead of the textual space. Thi…
CPMobius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning
Ran Li, Zeyuan Liu, Yinghao Chen +8
Large Language Models (LLMs) have demonstrated strong potential in complex reasoning, yet their progress remains fundamentally constrained by reliance on massive high-quality human…
Current Agents Fail to Leverage World Model as Tool for Foresight
Cheng Qian, Emre Can Acikgoz, Bingxuan Li +8
Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer…
CubeBench: Diagnosing Interactive, Long-Horizon Spatial Reasoning Under Partial Observations
Huan-ang Gao, Zikang Zhang, Tianwei Luo +9
Large Language Model (LLM) agents, while proficient in the digital realm, face a significant gap in physical-world deployment due to the challenge of forming and maintaining a robu…
JustRL: Scaling a 1.5B LLM with a Simple RL Recipe
Bingxiang He, Zekai Qu, Zeyuan Liu +9
Recent advances in reinforcement learning for large language models have converged on increasing complexity: multi-stage training pipelines, dynamic hyperparameter schedules, and c…
CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
Jiayu Liu, Cheng Qian, Zhaochen Su +4
Current evaluations of Large Language Model (LLM) agents primarily emphasize task completion, often overlooking resource efficiency and adaptability. This neglects a crucial capabi…
A Survey of Reinforcement Learning for Large Reasoning Models
Kaiyan Zhang, Yuxin Zuo, Bingxiang He +36
In this paper, we survey recent advances in Reinforcement Learning (RL) for reasoning with Large Language Models (LLMs). RL has achieved remarkable success in advancing the frontie…