papers.joyehuang.me

Paper Recommendations

Daily AI-powered curation from arXiv and Hugging Face Daily Papers. Last updated May 08, 2026 · 23:01 UTC.

Archive joyehuang.me Source
62
Candidates
5
Top Picks
0
Blockbusters
12
Max Score
Today's Picks

Editor's Rationale

**Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction** Core contribution: Proposes Direct Corpus Interaction (DCI), where agents search raw corpora using general-purpose terminal tools (grep, shell commands, etc.) instead of embedding-based retrieval APIs, outperforming strong sparse/dense/reranking baselines on IR and agentic search benchmarks. Why recommended: Directly challenges the fixed retrieve-then-reason paradigm of RAG. Highly relevant to Agent architecture design and Tool Use -- the interface resolution between agent and corpus may matter more than the retrieval algorithm itself. https://arxiv.org/abs/2605.05242 **SkillOS: Learning Skill Curation for Self-Evolving Agents** Core contribution: Proposes SkillOS, an experience-driven RL training recipe for learning skill curation in self-evolving agents. A frozen executor retrieves and applies skills while a trainable curator updates an external SkillRepo from accumulated experience. Why recommended: Agent self-evolution is a core interest area. This paper tackles the long-horizon curation policy learning problem under delayed feedback and generalizes across different executor backbones and task domains. https://arxiv.org/abs/2605.06614 **Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval** Core contribution: Introduces SIRA, which compresses multi-round exploratory search into a single corpus-discriminative retrieval action. Uses LLM offline vocabulary expansion + query-side evidence prediction + document-frequency filtering to form one weighted BM25 query. Why recommended: Very relevant to retrieval-augmented agent architecture. It shows that one well-formed lexical query can outperform expensive multi-round agentic search, while remaining training-free and highly interpretable. https://arxiv.org/abs/2605.06647 **When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning** Core contribution: Proposes Side-by-Side (SxS) Interleaved Reasoning, making disclosure timing a controllable decision within autoregressive generation. Interleaves partial disclosures with continued private reasoning, trained with SFT+RL to optimize accuracy-content-latency Pareto trade-offs. Why recommended: Highly relevant to Context management and reasoning pacing in agents. Useful inspiration for designing low-latency, high-accuracy streaming agent interfaces (e.g. real-time dialogue or tool-calling scenarios). https://arxiv.org/abs/2605.03314

Top Picks

5 papers
#01 12

Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction

Zhuofeng Li, Haoxiang Zhang, Cong Wei et al.
Modern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a single top-k retrieval step before reasoning. This abstraction is efficient, but for agentic search, it becomes a bottleneck: exact lexical co…
agentagenticreasoningbenchmarkembedding
#02 11

ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning

Zihan Lin, Xiaohan Wang, Jie Cao et al.
Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivization of positive rewards. Although methods like Negative Sample Reinforcement (NSR) mitigate this …
agentfunction callingreasoningRAGbenchmarkalignment
#03 10

Audio-Visual Intelligence in Large Foundation Models

You Qin, Kai Liu, Shengqiong Wu et al.
Audio-Visual Intelligence (AVI) has emerged as a central frontier in artificial intelligence, bridging auditory and visual modalities to enable machines that can perceive, generate, and interact in the multimodal real world. In the era of large foundation models, joint modeling o…
agentagenticreasoningRAGevaluationbenchmark
#04 10

RemoteZero: Geospatial Reasoning with Zero Human Annotations

Liang Yao, Fan Liu, Shengxiang Xu et al.
Geospatial reasoning requires models to resolve complex spatial semantics and user intent into precise target locations for Earth observation. Recent progress has liberated the reasoning path from manual curation, allowing models to generate their own inference chains. Yet a fina…
reasoningautonomousRAGDPOPPOGRPO
#05 9

Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Environments

Xiaoyu Yang, En Yu, Wei Duan et al.
This paper identifies a critical yet underexplored challenge in reasoning alignment from multiple multi-modal large language models (MLLMs): In non-stationary environments, the diverse reasoning distributions of source models often evolve unpredictably, transmitting systematic bi…
reasoningautonomousRAGbenchmarkalignment

All Candidates

62 papers
ScorePaperAuthorsCategory
9 When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning Jiaqi Wei, Xuehang Guo et al.
8 Superintelligent Retrieval Agent: The Next Frontier of Information Retrieval Zeyu Yang, Qi Ma et al. cs.IR, cs.AI, cs.LG
8 SkillOS: Learning Skill Curation for Self-Evolving Agents Siru Ouyang, Jun Yan et al.
8 Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key Tianle Wang, Zhaoyang Wang et al.
8 SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies Siddhant Saxena, Nilesh Trivedi et al.
7 Verifier-Backed Hard Problem Generation for Mathematical Reasoning Yuhang Lai, Jiazhan Feng et al. cs.LG, cs.AI, cs.CL
7 BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language Models Xin Gao, Ruiyi Zhang et al.
6 The Scaling Properties of Implicit Deductive Reasoning in Transformers Enrico Vompa, Tanel Tammet
6 Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO Zhiyuan Zeng, Jiameng Huang et al.
6 Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes Jingjie Ning, Xiaochuan Li et al.
5 Are We Making Progress in Multimodal Domain Generalization? A Comprehensive Benchmark Study Hao Dong, Hongzhao Li et al. cs.CV, cs.AI, cs.LG, cs.MM
5 Recursive Agent Optimization Apurva Gandhi, Satyaki Chakraborty et al. cs.LG, cs.AI, cs.CL, cs.MA
5 KernelBench-X: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels Han Wang, Jintao Zhang et al.
5 EDU-CIRCUIT-HW: Evaluating Multimodal Large Language Models on Real-World University-Level STEM Student Handwritten Solutions Weiyu Sun, Liangliang Chen et al.
5 TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding Minjie Qiang, Mingming Zhang et al.
5 Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration Langlin Huang, Chengsong Huang et al.
5 MiA-Signature: Approximating Global Activation for Long-Context Understanding Yuqing Li, Jiangnan Li et al.
5 XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity Dasol Choi, Eugenia Kim et al.
4 Generative Quantum-inspired Kolmogorov-Arnold Eigensolver Yu-Cheng Lin, Yu-Chao Hsu et al.
4 When to Trust Imagination: Adaptive Action Execution for World Action Models Rui Wang, Yue Zhang et al.
4 Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling Yuan Wang, Ouxiang Li et al.
4 Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Yaorui Shi, Yuxin Chen et al.
4 MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction Junbo Cui, Bokai Xu et al.
3 When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels Sushant Gautam, Finn Schwall et al. cs.LG, cs.AI, cs.CL
3 Edge-specific signal propagation on mature chromophore-region 3D mechanism graphs for fluorescent protein quantum-yield prediction Yuchen Xiong, Swee Keong Yeap et al. cs.LG
3 RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation Ivan Bondarenko, Roman Derunets et al.
3 ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving Huimin Wang, Yue Wang et al.
3 The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models Chonghan Qin, Xiachong Feng et al.
3 A Foundation Model for Zero-Shot Logical Rule Induction Yin Jun Phua
2 ActCam: Zero-Shot Joint Camera and 3D Motion Control for Video Generation Omar El Khalifi, Thomas Rossi et al. cs.CV, cs.AI, cs.LG
2 Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less Yuxing Liu, Jianyu Wang et al. cs.LG, cs.AI, math.OC
2 PianoCoRe: Combined and Refined Piano MIDI Dataset Ilya Borovik cs.SD, cs.LG
2 Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance Ziyun Zeng, Yiqi Lin et al.
2 Continuous Latent Diffusion Language Model Hongcan Guo, Qinyu Zhao et al.
2 MARBLE: Multi-Aspect Reward Balance for Diffusion RL Canyu Zhao, Hao Chen et al.
2 The First Token Knows: Single-Decode Confidence for Hallucination Detection Mina Gabriel
1 Why Global LLM Leaderboards Are Misleading: Small Portfolios for Heterogeneous Supervised ML Jai Moondra, Ayela Chughtai et al. cs.LG, cs.DM, cs.ET, math.OC
1 Crafting Reversible SFT Behaviors in Large Language Models Yuping Lin, Pengfei He et al. cs.LG
1 When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds Hongyi Tao, Dingzhi Yu et al. cs.LG, cs.AI, cs.CL, math.OC
1 Online Bayesian Calibration under Gradual and Abrupt System Changes Yang Xu, Chiwoo Park cs.LG, cs.ET, stat.ML
1 TIDE: Every Layer Knows the Token Beneath the Context Ajay Jaiswal, Lauren Hannah et al.
1 Diffusion Model as a Generalist Segmentation Learner Haoxiao Wang, Antao Xiang et al.
0 UniPool: A Globally Shared Expert Pool for Mixture-of-Experts Minbin Huang, Han Shi et al. cs.LG, cs.AI
0 Inductive Venn-Abers and related regressors Ivan Petej, Vladimir Vovk cs.LG
0 Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models Ronaldo Canizales, Divya Gopinath et al. cs.LG, cs.AI
0 Hybrid Quantum-Classical GANs for the Generation of Adversarial Network Flows Prateek Paudel, Nitin Jha et al. cs.LG
0 LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation Dan Jacobellis, Neeraja J. Yadwadkar eess.IV, cs.LG, cs.MM, eess.AS, eess.SP
0 The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity Siquan Li, Kaiqi Jiang et al. cs.LG, cs.AI, stat.ML
0 SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders Jakub Stępień, Marcin Mazur et al. cs.LG, cs.CV
0 GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs Pranav Mantini, Shishir K. Shah
0 Prescriptive Scaling Laws for Data Constrained Training Justin Lovelace, Christian Belardi et al.
0 A^2TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping Dingwei Chen, Zefang Zong et al.
0 SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation YaoYang Liu, Yuechen Zhang et al.
0 Recovering Hidden Reward in Diffusion-Based Policies Yanbiao Ji, Qiuchang Li et al.
0 TT4D: A Pipeline and Dataset for Table Tennis 4D Reconstruction From Monocular Videos Nima Rahmanian, Daniel Kienzle et al.
0 Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback Edoardo Bianchi, Antonio Liotta
-1 Continuous-Time Distribution Matching for Few-Step Diffusion Distillation Tao Liu, Hao Yan et al.