Scholarly Article
- agensh
- agent-skills-can-be-harmful
- agent-storage-footprint
- attention-is-all-you-have
- beyond-pass-at-1
- claw-swe-bench
- coding-agent-misalignment
- confucius-code-agent
- context-files-ablation-paper
- ddr-bench
- dream-rsi
- environment-evolution
- harness-bench
- harness-disclosure
- harnessdev
- hitchhikers-guide-agentic-ai
- how-many-tools-should-an-agent-see
- long-horizon-agents-survey
- mast-multi-agent-failure-taxonomy
- meaning-typed-programming
- model-or-harness-taxonomy
- scaffold-effects-gaia
- science-of-agent-reliability
- scienceide
- self-evolving-agents-survey
- skill-shadowing
- swe-bench
- swe-bench-illusion
- tau-bench
- webarena