Entities · Models
gpt-oss-120b
13 articles tagged with this entity.
-
Harness-Aware Self-Evolving: Co-Evolving Model Weights, Harness, and Task Solutions
-
Mechanism-level routing failure in LLMs over Lean-verified algebraic structures
-
GRACE-RAG: Governed Retrieval Architecture for Canonical Evidence Synthesis, Enabling Lightweight Deployment in Closed-Domain Institutional Settings
-
Benchmarking Large Language Models on Floating-Point Error Classification
-
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
-
Beyond Pass/Fail: Using Process Mining to Understand How LLMs Resist (and Fail) Red Team Attacks
-
Evaluation of LLMs for Mathematical Formalization in Lean
-
Improving Heart-Focused Medical Question Answering in LLMs via Variance-Aware Rubric Rewards with GRPO
-
ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces
-
Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation
-
Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
-
GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents
-
Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals