LLM Reasoning and Agent Memory - Research Digest

H$^2$R: Hierarchical Hint-Based Reward for Mathematical Reasoning via Reinforcement Learning

He Tu, Siye Li, Hongyi Wen

Source: arxiv

Don't Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation

Zheng Zhu, Xiaozhuan Liang, Xi Chen, Bei Yu, Jiaya Jia

Source: arxiv

Long-Term Agent Memory through Complementary Curation and Consolidation

Abhishek Gupta, Dongge Han, Daniel Madrigal Diaz, Wei-Ning Chen, Mayukh Das, Victor Rühle, Saravan Rajmohan

Source: arxiv

Heterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels

Qin-Wen Luo, Sheng Ren, Xiang Chen, Rui Liu, Jun Fang, Naiqiang Tan, Jun Wang, Hua Chai, Sheng-Jun Huang

Source: arxiv

Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps

Peitong Duan, Khashayar Gatmiry, Jeffrey Nichols, Samy Bengio, Emmanuel Abbe

Source: arxiv

MemSteer: Turning User Histories into Supervision for Agent Memory Optimization

Jie Huang, Cuiling Lan, Qize Yu, Xiulian Peng, Yan Lu

Source: arxiv

EpiAgent: Epistemic Self-Play for LLM Agents

Xuanfa Jin, Xinyu Cui, Zhijian Ma, Xue Yan, Jian Zhao, Haifeng Zhang, Jun Wang

Source: arxiv

Aligning Medical Vision Language Models at the Capability Boundary with Entropy Adaptive Rubric Grounding

Hongyu Bai, Jiaqi Zeng, Chunzheng Zhu

Source: arxiv

Distributional Reward Calibration and Budget-Neutral Credit Assignment for Multimodal RLVR

Lang Chen, Zongxin Xu, Borui Wang, Anran Liu, Shitong Chen

Source: arxiv

Reward-Adaptive Co-Evolution of Policy and Rubric

Yizhu Chen, Jianguang Jiang, Jiameng Huang, Chuyu Fang, Bojun Zhang, Zhenyu Jiao, Xing Yuan, Tong Lin

Source: arxiv

Retrieval as Traversal: Value-Indexed Memory for Stateful Long-Context Agents

Daniel Strauß, Zhenshan Bing, Alois Knoll

Source: arxiv Must Read

Locating and Closing Information Gaps in Multi-Agent Systems

Yaxin Gong, Chongming Gao, Gangyi Zhang, Chenxiao Fan, Leyang Shen, Jiakai Wang, Dong Wang, Yang Liu, Haoyan Liu, Xinting Hu

Source: arxiv Must Read

Sticky Collusion: Persistence of LLM Agent Collusion after Incentive Removal and Partner Replacement

Joshua Adrian Cahyono

Source: arxiv Must Read

Finding Is Not Returning, Returning Is Not Reconstructing: A Multi-Dimensional Evaluation of Agent Social Re-entry

Sheng Wan, Cong Ma, Sichen Dong, Qian'Ang Mao, Chenhan Zhang, Daning Hu, Qiang Yang

Source: arxiv Must Read

MAServeBench: Benchmarking Multi-Agent LLM Serving Systems with Hierarchical Collaboration Workloads

Shengxuan Qiu, Haochen Huang, Shuzhang Zhong, Zizhuo Fu, Zebin Yang, Jianming Tong, Meng Li

Source: arxiv Must Read

Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success

Amir H. Rezaeian, Weiyi Sun, Yassine Benajiba, Dan Roth

Source: arxiv Must Read

Cheap Retrieval and Observation Credit Assignment from One Quantity: The Value of Information

Daniel Strauss, Nikolaos Sotirakis, Zhenshan Bing, Alois Knoll

Source: arxiv Must Read

ShallowDefend: Harnessing Shallow Safety Alignment for Multi-Turn Defender

Qiyao Ma, Xiaodong Liu, Weiwei Yang, Mingqian Feng, Chengquan Guo, Jialin Song, Carolyn Buractaon, Zhe Zhao, Junshan Zhang, Sandeep Atluri, Christopher White, Jianfeng Gao

Source: arxiv Must Read

Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning

Guizhen Chen, Weiwen Xu, Wotao Yin, Anh Tuan Luu, Hou Pong Chan

Source: arxiv Must Read