papers.joyehuang.me

Paper Recommendations

Daily AI-powered curation from arXiv and Hugging Face Daily Papers. Last updated May 15, 2026 · 23:00 UTC.

Archive joyehuang.me Source
85
Candidates
5
Top Picks
0
Blockbusters
20
Max Score
Today's Picks

Editor's Rationale

**APWA: A Distributed Architecture for Parallelizable Agentic Workflows** (arXiv: 2605.15132) — Proposes APWA, a distributed multi-agent architecture that decomposes complex workflows into non-interfering subproblems processed independently without cross-communication, solving scaling bottlenecks for high-throughput parallel tasks. **Orchard: An Open-Source Agentic Modeling Framework** (arXiv: 2605.15040) — Microsoft's open-source lightweight framework for scalable agentic modeling with a sandbox lifecycle management service at its core, featuring three training recipes (coding agent, GUI agent, personal assistant agent) sharing reusable primitives across domains. **Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems** (arXiv: 2605.14892) — A survey organized around the LIFE progression (Lay foundation, Integrate agents, Find faults, Evolve), systematically examining collaboration patterns, error propagation, and self-improvement in multi-agent systems. **CAST: Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use** (arXiv: 2605.15041) — A case-driven framework that treats historical execution trajectories as structured cases to calibrate reasoning depth, achieving up to 5.85% accuracy gains on BFCLv2/ToolBench while reducing reasoning length by 26%.

Top Picks

5 papers
#01 20

APWA: A Distributed Architecture for Parallelizable Agentic Workflows

Evan Rose, Tushin Mallick, Matthew D. Laws et al.
cs.AI, cs.DC, cs.MA
Autonomous multi-agent systems based on large language models (LLMs) have demonstrated remarkable abilities in independently solving complex tasks in a wide breadth of application domains. However, these systems hit critical reasoning, coordination, and computational scaling bott…
agentmulti-agentagenticreasoningworkflowautonomous
#02 20

Orchard: An Open-Source Agentic Modeling Framework

Baolin Peng, Wenlin Yao, Qianhui Wu et al.
cs.AI, cs.CL
Agentic modeling aims to transform LLMs into autonomous agents capable of solving complex tasks through planning, reasoning, tool use, and multi-turn interaction with environments. Despite major investment, open research remains constrained by infrastructure and training gaps. Ma…
agentagentictool useplanningreasoningorchestration
#03 17

Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems

Shihao Qi, Jie Ma, Rui Xing et al.
LLM-based autonomous agents have demonstrated strong capabilities in reasoning, planning, and tool use, yet remain limited when tasks require sustained coordination across roles, tools, and environments. Multi-agent systems address this through structured collaboration among spec…
agentmulti-agenttool useplanningreasoningautonomous
#04 15

ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both

Ziyu Guo, Rain Liu, Xinyan Chen et al.
cs.CV, cs.AI, cs.CL
Visual reasoning, often interleaved with intermediate visual states, has emerged as a promising direction in the field. A straightforward approach is to directly generate images via unified models during reasoning, but this is computationally expensive and architecturally non-tri…
agentagenticreasoningbenchmarkGRPOembedding
#05 14

Why Neighborhoods Matter: Traversal Context and Provenance in Agentic GraphRAG

Riccardo Terrenzi, Maximilian von Zastrow, Serkan Ayvaz
cs.AI, cs.IR
Retrieval-Augmented Generation can improve factuality by grounding answers in external evidence, but Agentic GraphRAG complicates what it means for citations to be faithful. In these systems, an agent explores a knowledge graph before producing an answer and a small set of citati…
agentagenticRAGretrieval-augmentedevaluationPPO

All Candidates

85 papers
ScorePaperAuthorsCategory
14 Is Grep All You Need? How Agent Harnesses Reshape Agentic Search Sahil Sen, Akhil Kasturi et al. cs.CL
13 Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use Renning Pang, Tian Lan et al. cs.AI, cs.CL
13 RewardHarness: Self-Evolving Agentic Post-Training Yuxuan Zhang, Penghui Du et al.
12 Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models Frederik Schmitt, Matthias Cosler et al. cs.LG
12 WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation Shuangrui Ding, Xuanlang Dai et al.
12 Nexus : An Agentic Framework for Time Series Forecasting Sarkar Snigdha Sarathi Das, Palash Goyal et al.
11 CLOVER: Closed-Loop Value Estimation \& Ranking for End-to-End Autonomous Driving Planning Sining Ang, Yuguang Yang et al. cs.RO, cs.AI, cs.CV
11 Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding Valeriy Vyaltsev, Alsu Sagirova et al.
11 Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning Hanbo Cheng, Limin Lin et al.
10 MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory Minghao Guo, Qingyue Jiao et al. cs.CV, cs.CL, cs.IR
10 Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks Karthik Raghu Iyer, Yazdan Jamshidi et al. cs.CR, cs.CL
10 Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs Guangyu Feng, Huanzhi Mao et al. cs.CL, cs.AI, cs.LG
10 SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks Yusuke Ozaki, Dhaval Patel
9 Self-Distilled Agentic Reinforcement Learning Zhengxi Lu, Zhiyuan Yao et al. cs.LG, cs.AI, cs.CL
9 From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents Md Tahmid Rahman Laskar, Xue-Yong Fu et al. cs.CL
9 CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves Amirreza Mohseni, Mona Mohammadi et al.
8 Pelican-Unified 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action Yi Zhang, Yinda Chen et al. cs.RO, cs.AI
8 MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models Xiyu Ren, Zhaowei Wang et al.
7 FutureSim: Replaying World Events to Evaluate Adaptive Agents Shashwat Goel, Nikhil Chandak et al. cs.LG, cs.AI, cs.CL
7 Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands Pratinav Seth, Vinay Kumar Sankarapu cs.LG, cs.AI
7 PREPING: Building Agent Memory without Tasks Yumin Choi, Sangwoo Park et al.
7 EvolveMem:Self-Evolving Memory Architecture via AutoResearch for LLM Agents Jiaqi Liu, Xinyu Ye et al.
6 Quantitative Video World Model Evaluation for Geometric-Consistency Jiaxin Wu, Yihao Pi et al. cs.CV, cs.AI
6 OpenDeepThink: Parallel Reasoning via Bradley--Terry Aggregation Shang Zhou, Wenhao Chai et al. cs.AI
6 Evidential Reasoning Advances Interpretable Real-World Disease Screening Chenyu Lian, Hong-Yu Zhou et al. cs.CV, cs.AI, cs.LG
6 Understanding How International Students in the U.S. Are Using Conversational AI to Support Cross-Cultural Adaptation Laleh Nourian, Anisa Callis et al. cs.HC, cs.AI
6 On the Cultural Anachronism and Temporal Reasoning in Vision Language Models Mukul Ranjan, Prince Jha et al. cs.CV, cs.AI, cs.CL
6 From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG Guanhua Chen, Chuyue Huang et al. cs.CL
6 WildTableBench: Benchmarking Multimodal Foundation Models on Table Understanding In the Wild Junzhe Huang, Xiaoxiao Sun et al.
5 Text Knows What, Tables Know When: Clinical Timeline Reconstruction via Retrieval-Augmented Multimodal Alignment Sayantan Kumar, Shahriar Noroozizadeh et al. cs.CL, cs.AI, cs.LG, stat.ML
5 Hand-in-the-Loop: Improving Dexterous VLA via Seamless Interventional Correction Zhuohang Li, Liqun Huang et al. cs.RO, cs.LG
5 AI Knows When It's Being Watched: Functional Strategic Action and Contextual Register Modulation in Large Language Models Vinicius Covas, Jorge Alberto Hidalgo Toledo cs.CL, cs.AI, cs.CY, cs.MA
5 LiSA: Lifelong Safety Adaptation via Conservative Policy Induction Minbeom Kim, Lesly Miculicich et al.
5 Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning Taebong Kim, Youngsik Hong et al.
5 Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling Yafu Li, Runzhe Zhan et al.
5 Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis Yucheng Shi, Zhenwen Liang et al.
4 EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation Ruozhen He, Meng Wei et al. cs.CV, cs.AI
4 Logging Policy Design for Off-Policy Evaluation Connor Douglas, Joel Persson et al. stat.ML, cs.AI, cs.IR, cs.LG, stat.ME
4 ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World Ziyin Zhang, Zihan Liao et al. cs.CL, cs.AI
4 Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation Che Liu, Lichao Ma et al.
4 PanoWorld: Towards Spatial Supersensing in 360^circ Panorama World Changpeng Wang, Xin Lin et al.
4 IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation Shijie Lian, Bin Yu et al.
3 Eradicating Negative Transfer in Multi-Physics Foundation Models via Sparse Mixture-of-Experts Routing Ellwil Sharma, Arastu Sharma cs.LG, cs.AI, physics.comp-ph
3 Long Context Pre-Training with Lighthouse Attention Bowen Peng, Subho Ghosh et al.
3 PreScam: A Benchmark for Predicting Scam Progression from Early Conversations Weixiang Sun, Shang Ma et al.
3 ViMU: Benchmarking Video Metaphorical Understanding Qi Li, Xinchao Wang
3 FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale Runyuan He, Qiuyang Mang et al.
3 Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning Zihao Han, Tiangang Zhang et al.
2 Improving Multi-turn Dialogue Consistency with Self-Recall Thinking Renning Pang, Tian Lan et al. cs.CL, cs.AI
2 RefDecoder: Enhancing Visual Generation with Conditional Video Decoding Xiang Fan, Yuheng Wang et al. cs.CV, cs.LG
2 Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution Saisab Sadhu, Pratinav Seth et al. cs.LG, cs.CL, cs.ET
2 Training ML Models with Predictable Failures Will Schwarzer, Scott Niekum cs.LG
2 Causal Foundation Models with Continuous Treatments Christopher Stith, Medha Barath et al. cs.LG
2 Learning from Language Feedback via Variational Policy Distillation Yang Li, Erik Nijkamp et al. cs.LG
2 Aligning Latent Geometry for Spherical Flow Matching in Image Generation Tuna Han Salih Meral, Kaan Oktay et al.
2 Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance Kai Yan, Alexander G. Schwing et al.
2 Realiz3D: 3D Generation Made Photorealistic via Domain-Aware Learning Ido Sobol, Kihyuk Sohn et al.
2 PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution Zihang Xu, Xiaoyang Liu et al.
2 RouteProfile: Elucidating the Design Space of LLM Profiles for Routing Jingjun Xu, Hongji Pu et al.
2 DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models Quanhao Li, Junqiu Yu et al.
2 LLM-based Detection of Manipulative Political Narratives Sinclair Schneider, Florian Steuber et al.
1 MeMo: Memory as a Model Ryan Wei Heng Quek, Sanghyuk Lee et al. cs.CL, cs.AI, cs.LG
1 Widening the Gap: Exploiting LLM Quantization via Outlier Injection Xiaohua Zhan, Kazuki Egashira et al. cs.LG, cs.AI
1 RoSHAP: A Distributional Framework and Robust Metric for Stable Feature Attribution Lanxin Xiang, Liang Shi et al. stat.ML, cs.LG
1 Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image Ming Qian, Zimin Xia et al.
1 Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models Yanyan Zhang, Chaoda Song et al.
1 Dynamic Latent Routing Fangyuan Yu, Xin Su et al.
1 Does Synthetic Layered Design Data Benefit Layered Design Decomposition? Kam Man Wu, Haolin Yang et al.
1 SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer Haoyi Zhu, Haozhe Liu et al.
1 Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video Yifan Wang, Tong He
1 PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation Yidong Huang, Zun Wang et al.
0 VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction Kaixin Zhu, Yiwen Tang et al. cs.CV, cs.AI
0 When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability ML Nissen Gonzalez, Melwina Albuquerque et al. cs.LG
0 CoCo-InEKF: State Estimation with Learned Contact Covariances in Dynamic, Contact-Rich Scenarios Michael Baumgartner, David Müller et al. cs.RO, cs.LG, eess.SY
0 Proposal and study of statistical features for string similarity computation and classification E. O. Rodrigues, D. Casanova et al. cs.LG, cs.CL, cs.IT
0 MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs Rui Wen, Mark Russinovich et al. cs.CR, cs.CL
0 BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE Juntong Wu, Jialiang Cheng et al.
0 Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models Yicheng Ji, Zhizhou Zhong et al.
0 Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation Min Zhao, Hongzhou Zhu et al.
0 Topology-Preserving Neural Operator Learning via Hodge Decomposition Dongzhe Zheng, Tao Zhong et al.