81 citations · 301 across the 80 of their papers we have counts for
88 papers
Mosaic: Multi-Session Agentic Reinforcement Learning
Yilong Xu, Minrui Xu, Xinyu Zhou +3
Most existing agentic reinforcement learning methods assume single-session trajectories, where interaction proceeds within one continuously accumulated context. However, agentic te…
Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents
Zilin Wang, Yinhong Liu, Chao Chen +2
Large language model agents solve tasks through long sequences of tool calls, and the prevailing design has a single strong model generate every step, although many steps are routi…
Action-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Bias
Yinhong Liu, Zhili Tan, Zilin Wang +1
Large Language Models (LLMs) have shown strong performance on tool-use agentic tasks when given a fixed tool schema. Yet a tool schema is not the action space of an agent; it is me…
Entropy Can Flow, or It Can Guide. Be Entropy. LEDFlow: Introducing Entropy-guided Generation Order into Uniform Discrete Flow
Tung Sum Thomas Kwok, Yidong Ouyang, Yingjia Wan +3
Uniform discrete flow permits repeated updates at every generation position. While continued revision supports correction of wrong tokens, it also exposes correct intermediate pred…
Disorder-induced conducting edges on Kagomé lattice
A. Chmeruk, D. Jones, L. Chioncel
Within a cluster extension of the coherent potential approximation, disorder averaging generates a non-local self-energy that renormalizes both diagonal and off-diagonal hopping te…
MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off
Songxin Lei, Kun Ouyang, Weilin Ruan +4
Long-horizon LLM agents require memory systems that recover useful evidence from large interaction histories without passing excessive context to downstream models. Existing memory…
FormalRx: Rectify and eXamine Semantic Failures in Autoformalization
Haocheng Wang, Baiyu Huang, Yingjia Wan +4
The veracious semantic alignment in autoformalization is significant for formal mathematical reasoning. However, existing evaluations provide only opaque binary verdicts or scalar…
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction
Mingzhe Du, Luu Anh Tuan, Tianyi Wu +4
Repository-level vulnerability reproduction is a demanding software engineering (SE) task: an agent must inspect a codebase, infer the input grammar that reaches a vulnerable path,…
From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning
Chao Chen, Chengzu Li, Zhiwei Li +2
Reinforcement learning pipelines for Large Language Model (LLM) training often rely on manually redesigned environments between stages, requiring practitioners to heuristically inf…
Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning
Jiayu Yang, Chao Chen, Shengen Wu +6
Latent chain-of-thought compresses reasoning through continuous hidden-state recurrence, but existing approaches are difficult to optimize with standard on-policy reinforcement lea…
Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning
Zhicheng Yang, Zhijiang Guo, Yifan Song +5
On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models. However, scaling OPD to long-horizon tasks exposes a critical flaw: as the student's gener…
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
Minrui Xu, Zilin Wang, Mengyi DENG +12
Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and…
From Table to Cell: Attention for Better Reasoning with TABALIGN
Tung Sum Thomas Kwok, Zeyong Zhang, Xinyu Wang +6
Multi-step LLM reasoning over structured tables fails because planning and execution share no explicit cell-grounding contract. Existing methods constrain the planner to a left-to-…
DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization
Mengyi Deng, Zhiwei Li, Xin Li +4
Although Large Language Models (LLMs) have made remarkable progress, current preference optimization methods still struggle to align directional consistency while preserving reason…
ReaLB: Real-Time Load Balancing for Multimodal MoE Inference
Yingping Wang, Yi Wu, Xiangyu Wu +4
Mixture-of-Experts (MoE) architectures are widely used in modern large language models and multimodal models. However, inference efficiency is often limited by highly dynamic and s…
CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation
Zaoyu Chen, Jianbo Dai, Boyu Zhu +6
Large language models (LLMs) can generate code from natural language, but the extent to which they capture intended program behavior remains unclear. Executable behavioral specific…
Spotlight and Shadow: Attention-Guided Dual-Anchor Introspective Decoding for MLLM Hallucination Mitigation
Yebo Wu, Han Jin, Zhijiang Guo +1
Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities yet continue to suffer from hallucination, where generated text contradicts visual cont…
Skip-Connected Policy Optimization for Implicit Advantage
Fengwei Teng, Jinyi Bai, Xinhao Yao +3
Group Relative Policy Optimization (GRPO) has proven effective in RLVR by using outcome-based rewards. While fine-grained dense rewards can theoretically improve performance, we re…
DeReason: A Difficulty-Aware Curriculum Improves Decoupled SFT-then-RL Training for General Reasoning
Hanxu Hu, Yuxuan Wang, Maggie Huan +4
Reinforcement learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for eliciting reasoning capabilities in large language models, particularly in mathematics…
When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?
Xinyu Zhou, Chang Jin, Carsten Eickhoff +2
Large language models (LLMs) rarely admit uncertainty, often producing fluent but misleading answers, rather than abstaining (i.e., refusing to answer). This weakness is even evide…
Efficient RLVR Training via Weighted Mutual Information Data Selection
Xinyu Zhou, Boyu Zhu, Haotian Zhang +2
Reinforcement learning (RL) plays a central role in improving the reasoning and alignment of large language models, yet its efficiency critically depends on how training data are s…
Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations
Yuxuan Yao, Haonan Sheng, Qingsong Lv +11
The escalating scale of Large Language Models (LLMs) necessitates efficient adaptation techniques. Model merging has gained prominence for its efficiency and controllability. Howev…
CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
Xiao Zhu, Xinyu Zhou, Boyu Zhu +5
Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scala…
Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning
Zhicheng Yang, Zhijiang Guo, Yinya Huang +5
Scaling test-time compute via long Chain-of-Thought unlocks remarkable gains in reasoning capabilities, yet it faces practical limits due to the linear growth of KV cache and quadr…