Paper page - Do not copy and paste! Rewriting strategies for code retrieval
… AI-generated summary Embedding-based code retrieval often suffers when encoders overfit to surface syntax. …
Search
Paper page - StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
… StraTA samples a compact strategy from the initial task state, conditions subsequent actions on that strategy, and trains strategy generation and action execution jointly with a hierarchical GRPO-style rollout design, further enhanced by diverse strategy rollout and critical self-judgment . …
Paper page - Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
… The following papers were recommended by the Semantic Scholar API PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training 2026 Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model 2026 Accelerating RL Post-Training Rollouts via System-Integ… …
Paper page - LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
Papers arxiv:2605.08083 LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling Published on May 8 Submitted by Chengsong Huang on May 11 3 Paper of the day Google Authors: Tong Zheng , , , , , , Runpeng Dai , , , Tianyi Xiong , , , Abstract AutoTTS automates test-time scaling strategy discove… …
Paper page - MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments
… AI-generated summary The Model Context Protocol MCP has unified the interface between Large Language Models LLMs and external tools, yet a fundamental gap remains in how agents conceptualize the environments within which they operate. …
Paper page - SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training
… In this work, we systematically study MoE compression in large-scale pretraining, focusing on three key questions: whether pruning provides a better initialization than training from scratch, how expert compression choices affect the final model after continued training , and which training strateg… …
Paper page - TMAS: Scaling Test-Time Compute via Multi-Agent Synergy
… Interesting breakdown of this paper on arXivLens: https://arxivlens.com/PaperView/Details/tmas-scaling-test-time-compute-via-multi-agent-synergy-682-9aa2c46a Covers the executive summary, detailed methodology, and practical applications. …
Paper page - Qwen-Image-VAE-2.0 Technical Report
… Moreover, we scale training to billions of images and incorporate a synthetic rendering engine to improve performance in text-rich scenarios. …
Paper page - Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
… This methodology enhances the feed-forward paradigm by integrating novel geometric constraints with a perspective-view training strategy , explicitly countering the primary sources of geometric error. This geometry-centric strategy yields a dramatic leap in both 3D accuracy and photorealism. …
Paper page - ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
… AI-generated summary Existing emotional support conversation ESC systems mainly rely on end-to-end response generation or coarse strategy supervision, offering limited interpretability and little support for systematic skill improvement. …