Tag: swe-bench

Sep 01, 2026

• reward-hacking
• specification-gaming
• benchmark-integrity
• held-out-tests
• cot-monitoring
• obfuscation
• swe-bench
• evaluation
• oversight-surface
• goodharts-law
• type/concept

Aug 30, 2026

• karthik-narasimhan
• princeton-nlp
• react
• swe-bench
• language-agents
• benchmarks
• reasoning-and-acting
• type/entity
• kind/person

Aug 30, 2026

• swe-bench
• benchmark
• github-issues
• code-generation
• iclr-2024
• swe-llama
• claude-2
• evaluation
• princeton-nlp
• swe-bench-verified
• swe-bench-pro
• type/source
• kind/paper

Aug 30, 2026

• agents-md
• claude-md
• context-files
• repository-context
• swe-bench
• inference-cost
• negative-result
• eth-zurich
• context-engineering
• prompt-engineering
• type/source
• kind/paper

May 09, 2026

• agent-harness
• harness-engineering
• subtraction-principle
• llm-non-determinism
• dspy
• natural-language-harness
• transferable-harness
• terminal-bench-2
• swe-bench
• ablation
• type/source
• kind/video