14 papers
MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents
Huanyao Zhang, Jiepeng Zhou, Jiaye Lin +9
Multimodal deep search is moving from short queries to long-horizon investigations that continually acquire evidence. However, training such agents remains constrained by limited c…
Long SKILL Compliance as Logical Reasoning: Closure-Grounded Detection with Scaling-Guided On-Policy Distillation
Shuaitao Zhao, Feng Ni, Lichao Ma +4
The increasing complexity of enterprise business scenarios has promoted the widespread adoption of long SKILL documents in agent systems, posing new challenges for compliance detec…
How Much, Then Where: Credit-Conserving Action-to-Token Allocation for Multi-Turn Agent Reinforcement Learning
Lichao Ma, Yang Sun, Shuaitao Zhao +9
Credit assignment in multi-turn agent reinforcement learning operates at two levels: assigning trajectory-level credit to actions and distributing each action's credit across its t…
Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
Yi Yang, Cong Qin, Xiaodan Liu +8
Large language model agents are commonly trained through reinforcement learning with sparse trajectory-level rewards, which offer limited guidance on how strongly individual tokens…
From Brewing to Resolution: Tracing the Internal Lifecycle of Code Reasoning in LLMs
Siyue Chen, Yifu Guo, Yuquan Lu +9
Standard accuracy metrics cannot explain why LLMs handle variable tracking but fail on semantically equivalent loops. We study an internal lifecycle of code reasoning in which mode…
Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning
Chishui Chen, Jiaye Lin, Te Sun +6
Agent skills are callable procedural modules that provide reusable knowledge and execution policies for complex agentic tasks. However, existing methods mainly focus on selecting r…
BrowseComp-: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents
Huanyao Zhang, Jiepeng Zhou, Bo Li +22
Multimodal large language models (MLLMs), equipped with increasingly advanced planning and tool-use capabilities, are evolving into autonomous agents capable of performing multimod…
Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training
Yangyi Fang, Jiaye Lin, Xiaoliang Fu +4
Multi-turn LLM agents are becoming pivotal to production systems, spanning customer service automation, e-commerce assistance, and interactive task management, where accurately dis…
How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization
Yangyi Fang, Jiaye Lin, Xiaoliang Fu +6
Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for Large Language Model (LLM) reasoning, yet current methods face key challenges in resource allocation…
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning
Xiaoliang Fu, Jiaye Lin, Yangyi Fang +7
Existing Reinforcement Learning with Verifiable Rewards (RLVR) algorithms, such as GRPO, rely on rigid, uniform, and symmetric trust region mechanisms that are fundamentally misali…
Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestration
Yifu Guo, Zishan Xu, Zhiyuan Yao +6
Existing multimodal reasoning models and frameworks suffer from fundamental architectural limitations: most lack the human-like ability to autonomously explore diverse reasoning pa…
Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems
Xuxin Cheng, Ke Zeng, Zhiquan Cao +65
Enhancing customer experience is essential for business success, particularly as service demands grow in scale and complexity. Generative artificial intelligence and Large Language…
SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
Jiaye Lin, Yifu Guo, Yuzhen Han +11
Large Language Model (LLM)-based agents have recently shown impressive capabilities in complex reasoning and tool use via multi-step interactions with their environments. While the…
RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
Huacan Wang, Ziyi Ni, Shuo Zhang +11
The ultimate goal of code agents is to solve complex tasks autonomously. Although large language models (LLMs) have made substantial progress in code generation, real-world tasks t…