Vela: User Behavior as Supervision Sparks LLM Intelligence
cs.CL, cs.AI
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/AllSpark-Research/Vela
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Phi-4 Technical Report
- CORAL: An LLM-Native Harness for Production Recommender Systems
- DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona Modeling
- Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- CL-bench Life: Can Language Models Learn from Real-Life Context?
- CL-bench: A Benchmark for Context Learning
- UXBench: Benchmarking User Experience in AI Assistants
- Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scale
- LiveAgentBench: Comprehensive Benchmarking of Agentic Systems Across 104 Real-World Challenges
- User-LLM: Efficient LLM Contextualization with User Embeddings
- Generalizing Verifiable Instruction Following
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Gemma 4 Technical Report
- Kimi K3: Open Frontier Intelligence
- Will we run out of data? Limits of LLM scaling based on human-generated data
- StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarios
- OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering