Key papers

• GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models (2025)
  GLM-4. 5 Team et al.
  5.10
• The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning (2026)
  Ishan S. Kshirsagar
  4.39
• QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL (2025)
  Cong Yu et al.
  3.10
• Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL (2025)
  Mohammadreza Pourreza et al.
  2.71
• LLM Scheming Inversely Scales with Pretraining Language Coverage (2026)
  Nathan Truong et al.
  2.00
• Where Steering Signals Come From: Activation Source Selection in Activation Steering (2026)
  Jiaran Ye et al.
  2.00
• CAST: Game Solvers as Turn-Level Teachers for LLM Agents (2026)
  Yu Wang et al.
  2.00
• Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising (2026)
  Tianci Liu et al.
  2.00
• Rank-Then-Act: Reward-Free Control from Frame-Order Progress (2026)
  Yuriy Maksyuta et al.
  2.00
• Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling (2026)
  Xiang Hu et al.
  2.00
• SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models (2026)
  Changti Wu et al.
  2.00
• Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing (2026)
  Tommaso Cerruti et al.
  2.00
• DrugGen 2: A disease-aware language model for enhancing drug discovery (2026)
  Ali Motahharynia et al.
  2.00
• EpiCaR: Knowing What You Don't Know Matters for Better Reasoning in LLMs (2026)
  Jewon Yeom et al.
  1.94
• Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents (2026)
  Wenxuan Ding et al.
  1.94
• WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning (2026)
  Juyong Jiang et al.
  1.94
• Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning (2026)
  Banghao Chi et al.
  1.94
• Learning to Trigger: Reinforcement Learning at the Large Hadron Collider (2026)
  Zixin Ding et al.
  1.94
• Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR (2026)
  Yongjin Yang et al.
  1.94
• Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly? (2026)
  Tyler Ga Wei Lum et al.
  1.94
• The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning (2026)
  Jing Liang et al.
  1.94
• Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning (2026)
  Junha Jung et al.
  1.94
• TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning (2026)
  Yuanda Xu et al.
  1.94
• Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs (2026)
  Gabrielle Kaili-May Liu et al.
  1.94
• QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents (2026)
  Sergio Hernández-Gutiérrez et al.
  1.94
• VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement (2026)
  Seohyun Lee et al.
  1.94
• Spectral Rewiring for Exploration, Purification, and Model Merging (2026)
  Zhilong Zhang et al.
  1.94
• LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL (2026)
  Yujin Kim et al.
  1.94
• Weak-to-Strong Generalization via Direct On-Policy Distillation (2026)
  Shiyuan Feng et al.
  1.94
• UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma (2026)
  Chongyu Fan et al.
  1.94
• Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning (2026)
  Zhenyu Hou et al.
  1.94
• Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning (2026)
  Chen Tang et al.
  1.94
• Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms (2026)
  Ezgi Korkmaz
  1.94
• Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization (2026)
  Zhicheng Cai et al.
  1.94
• GRASP: GRanularity-Aware Search Policy for Agentic RAG (2026)
  Varun Gandhi et al.
  1.94
• SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning (2026)
  Mingyuan Wu et al.
  1.94
• Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning (2026)
  Xinyu Tang et al.
  1.94
• Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization (2026)
  Weiwen Xu et al.
  1.94
• SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning (2026)
  Jinyang Wu et al.
  1.94
• On-Policy Delta Distillation (2026)
  Byeongho Heo et al.
  1.94
• Recursive Harness Self-Improvement (2026)
  Hyunin Lee et al.
  1.94
• Understanding Reasoning from Pretraining to Post-Training (2026)
  Jingyan Shen et al.
  1.94
• LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks (2026)
  Tianzhu Ye et al.
  1.94
• Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning (2026)
  Junyao Yang et al.
  1.94
• ISO: An RLVR-Native Optimization Stack (2026)
  Hanqing Zhu et al.
  1.94
• SLPO: Scaling Latent Reasoning via a Surrogate Policy (2026)
  Runyang You et al.
  1.94
• Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning (2026)
  Md Tanvirul Alam
  1.94
• AREX: Towards a Recursively Self-Improving Agent for Deep Research (2026)
  Shuqi Lu et al.
  1.94
• Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills (2026)
  Siyuan Huang et al.
  1.94
• From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search (2026)
  Junlin Liu et al.
  1.94
• SEVerA: Verified Synthesis of Self-Evolving Agents (2026)
  Debangshu Banerjee et al.
  1.78
• Favia: Forensic Agent for Vulnerability-fix Identification and Analysis (2026)
  André Storhaug et al.
  1.72
• Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts (2026)
  Chen Yang et al.
  1.72
• Controllable LLM Reasoning via Sparse Autoencoder-Based Steering (2026)
  Yi Fang et al.
  1.67
• SERA: Soft-Verified Efficient Repository Agents (2026)
  Ethan Shen et al.
  1.67
• Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrieval (2025)
  Subhendu Khatuya et al.
  1.50
• RePro: Training Language Models to Faithfully Recycle the Web for Pretraining (2025)
  Zichun Yu et al.
  1.50
• Learning to Reason as Action Abstractions with Scalable Mid-Training RL (2025)
  Shenao Zhang et al.
  1.44
• PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning (2025)
  Keer Lu et al.
  1.39
• Med-R$^3$: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learning (2025)
  Keer Lu et al.
  1.33