Entities · Models
Qwen3-32B
18 articles tagged with this entity.
-
SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference
-
Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents
-
OpenThoughts-Agent: Data Recipes for Agentic Models
-
A Neuro-Symbolic Approach to Strategy Synthesis for Strategic Logics
-
$\tau$-Rec: A Verifiable Benchmark for Agentic Recommender Systems
-
Multimodal Approaches for Visually-Rich Document Type Classification: A Comparative Analysis
-
Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery
-
REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge
-
MLIPilot: LLM-Driven Auto-Research for Machine-Learned Interatomic Potentials
-
BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents
-
The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure
-
Semantic Flow Regularization: Teaching LLMs to Generate Diverse Yet Coherent Responses
-
Decompose-and-Refine: Structured Legal Question Answering with Parametric Retrieval
-
AstroMind: A High-Fidelity Benchmark for Spacecraft Behavior Reasoning Based on Large Language Models
-
Geo-Expert: Towards Expert-Level Geological Reasoning via Parameter-Efficient Fine-Tuning
-
Tool-Call Dependency Structure is Linearly Decodable in LLM Agent Residual Streams
-
Beyond Literal Translation: Evaluating Cultural Effectiveness in Social Media UGC
-
Model Spec Midtraining: Improving How Alignment Training Generalizes