1 citations · 3 across the 43 of their papers we have counts for
22 papers · 1 filter
Agent-R: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis
Teng Pan, Zixuan Wang, Yuchen Yan +5
Large language models have made rapid progress in agentic reasoning and tool use, raising expectations for agents that can take over realistic productivity work from humans. Howeve…
RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning
Yan Yu, Zhengxi Lu, Yizhou Liu +8
Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-le…
When Metrics Reward the Worst Translations: Internalizing Cultural Reasoning for Social Media Translation Evaluation
Yiwen Qiu, Linjuan Wu, Dingming Li +7
Automatic translation quality metrics trained on general-domain corpora systematically fail on social media content, where communicative intent is encoded in culturally loaded expr…
PaperGym: Rubric-Centered Evolution for Research-Plan Generation
Yuhan Wang, Zhengxi Lu, Yuchen Yan +6
Research planning is the decisive capability of AI scientists. Yet a research plan admits no verifiable answer, so reinforcement learning lacks the environment it requires: tasks p…
TTPO: Test-Time Policy Optimization
Aozhe Wang, Zhengxi Lu, Jianze Wang +8
Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large l…
BrowserForge: Scaling Web Episode via Parallel Browser Sandboxes
Fei Tang, Huawen Shen, Zhiqiong Lu +7
Web agents that act from rendered pixels avoid the fragility and heavy token cost of reading a page's HTML or accessibility tree, but training them depends on large amounts of high…
Pass the Baton: Trajectory-Relayed On-Policy Distillation
Haolei Xu, Xiaowen Xu, Haiwen Hong +5
On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix failure: once the student commits to a wrong reasoning directi…
Beyond Literal Translation: Evaluating Cultural Effectiveness in Social Media UGC
Linjuan Wu, Ruiqi Zhang, Xinze Lyu +7
Social media platforms enable large-scale cross-lingual communication, but translating user-generated content (UGC) remains challenging due to its informal style, cultural referenc…
Milestone-Guided Policy Learning for Long-Horizon Language Agents
Zixuan Wang, Yuchen Yan, Hongxing Li +7
While long-horizon agentic tasks require language agents to perform dozens of sequential decisions, training such agents with reinforcement learning remains challenging. We identif…
Language as a Latent Variable for Reasoning Optimization
Linjuan Wu, Haoran Wei, Jialong Tang +4
As LLMs reduce English-centric bias, a surprising trend emerges: non-English responses sometimes outperform English on reasoning tasks. We hypothesize that language functions as a…
Pause or Fabricate? Training Language Models for Grounded Reasoning
Yiwen Qiu, Linjuan Wu, Yizhou Liu +9
Large language models have achieved remarkable progress on complex reasoning tasks. However, they often implicitly fabricate information when inputs are incomplete, producing confi…
CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution
Teng Pan, Yuchen Yan, Zixuan Wang +6
Label-free reinforcement learning enables large language models to improve reasoning capabilities without ground-truth supervision, typically by treating majority-voted answers as…
Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning
Aozhe Wang, Yuchen Yan, Nan Zhou +5
Reinforcement learning for code generation relies on verifiable rewards from unit test pass rates. Yet high-quality test suites are scarce, existing datasets offer limited coverage…
InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning
Yuchen Yan, Liang Jiang, Jin Jiang +7
Large reasoning models achieve strong performance by scaling inference-time chain-of-thought, but this paradigm suffers from quadratic cost, context length limits, and degraded rea…
EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes
Yuqin Dai, Guoqing Wang, Yuan Wang +13
Retrieval-Augmented Generation (RAG) has advanced open-domain question answering by incorporating external information into model reasoning. However, effectively leveraging externa…
Active Confusion Expression in Large Language Models: Leveraging World Models toward Better Social Reasoning
Jialu Du, Guiyang Hou, Yihui Fu +4
While large language models (LLMs) excel in mathematical and code reasoning, we observe they struggle with social reasoning tasks, exhibiting cognitive confusion, logical inconsist…
EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering
Haolei Xu, Xinyu Mei, Yuchen Yan +5
Large language model (LLM) steering has emerged as a promising paradigm for controlling model behavior at inference time through targeted manipulation of hidden states, offering a…
Cooper: Co-Optimizing Policy and Reward Models in Reinforcement Learning for Large Language Models
Haitao Hong, Yuchen Yan, Xingyu Wu +5
Large language models (LLMs) have demonstrated remarkable performance in reasoning tasks, where reinforcement learning (RL) serves as a key algorithm for enhancing their reasoning…
GroundAct: Can LLM Agents Ground Actions in Environmental States?
Zixuan Wang, Dingming Li, Hongxing Li +8
LLM agents achieve 85-96% success on tasks where instructions fully specify the action, but drop to 29-53% when action feasibility depends on environmental state that the instructi…
VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models
Yuchen Yan, Jin Jiang, Zhenbang Ren +9
Large reasoning models such as OpenAI o1 and DeepSeek-R1 have demonstrated remarkable performance in complex reasoning tasks. A critical component of their training is the incorpor…
Let LRMs Break Free from Overthinking via Self-Braking Tuning
Haoran Zhao, Yuchen Yan, Yongliang Shen +7
Large reasoning models (LRMs), such as OpenAI o1 and DeepSeek-R1, have significantly enhanced their reasoning capabilities by generating longer chains of thought, demonstrating out…
MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task
Yuchen Yan, Yongliang Shen, Yang Liu +5
Mathematical reasoning represents a critical frontier in advancing large language models (LLMs). While step-by-step approaches have emerged as the dominant paradigm for mathematica…