From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery Paper ⢠2610.09684 ⢠Published Oct 7 ⢠18
Towards a Densing Law for User Representation Learning at Billion-Scale Capacity Paper ⢠2608.23392 ⢠Published Aug 24 ⢠28
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning Paper ⢠2608.05987 ⢠Published Aug 6 ⢠83
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning Paper ⢠2607.14777 ⢠Published Jul 16 ⢠104
OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning Paper ⢠2606.26790 ⢠Published Jun 25 ⢠59
Share More, Search Less: Collaborative Parallel Thinking for Efficient Test-Time Scaling Paper ⢠2605.27030 ⢠Published May 26 ⢠29
SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization Paper ⢠2604.02268 ⢠Published Apr 2 ⢠99
Query as Anchor: Scenario-Adaptive User Representation via Large Language Model Paper ⢠2602.14492 ⢠Published Feb 16 ⢠13
How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning Paper ⢠2602.10622 ⢠Published Feb 11 ⢠23
Do Not Waste Your Rollouts: Recycling Search Experience for Efficient Test-Time Scaling Paper ⢠2601.21684 ⢠Published Jan 29 ⢠10
Boosting Large Language Models for Mental Manipulation Detection via Data Augmentation and Distillation Paper ⢠2505.15255 ⢠Published May 21, 2025 ⢠5
Condition Errors Refinement in Autoregressive Image Generation with Diffusion Loss Paper ⢠2602.07022 ⢠Published Feb 2 ⢠19
OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions Paper ⢠2602.05843 ⢠Published Feb 5 ⢠61
Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning Paper ⢠2601.20209 ⢠Published Jan 28 ⢠25
Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning Paper ⢠2601.03872 ⢠Published Jan 7 ⢠45
HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices Paper ⢠2512.14052 ⢠Published Dec 16, 2025 ⢠43
From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks Paper ⢠2512.02580 ⢠Published Dec 2, 2025 ⢠28
Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning Paper ⢠2512.01282 ⢠Published Dec 1, 2025 ⢠3
Kardia-R1 Collection Model Weight and Dataset of our WWW 2026 paper: Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric ⢠3 items ⢠Updated Mar 15 ⢠1