๐ŸŽ CS329T ยท ๆ–ฏๅฆ็ฆ๐Ÿ“ ่ทฏๅพ„ไธ€ ยท Agentic

CS329T ยท Trustworthy ML / Agentic AI

ไธป่ฎฒ๏ผšAnupam Dattaใ€John Mitchell ๏ฝœ Autumn 2025 ๏ฝœ ๅฎ˜็ฝ‘๏ผšhttps://web.stanford.edu/class/cs329t
๐ŸŽฌ ๆ— ๅฎ˜ๆ–นๅฝ•ๆ’ญ๏ผ›่ฎฒไน‰+่ฎบๆ–‡ๅทฒๆœฌๅœฐๅŒ–

ๆœฌๅœฐๆๆ–™

homeworks๏ผˆ1๏ผ‰

๐Ÿ“„ CS329T_HW1_Fall2025.pdf

papers๏ผˆ22๏ผ‰

๐Ÿ“„ agent_as_a_judge.pdf๐Ÿ“„ agent_gpa_goal_plan_action_alignment.pdf๐Ÿ“„ agentharm_benchmark_harmfulness_llm_agents.pdf๐Ÿ“„ are_scaling_up_agent_environments.pdf๐Ÿ“„ dapo_open_source_llm_rl_at_scale.pdf๐Ÿ“„ eval_benchmark_llm_agents_survey.pdf๐Ÿ“„ gepa_reflective_prompt_evolution.pdf๐Ÿ“„ grounding_and_evaluation_llms.pdf๐Ÿ“„ harmbench_standardized_eval_red_teaming.pdf๐Ÿ“„ improving_alignment_robustness_circuit_breakers.pdf๐Ÿ“„ naturalthoughts_reasoning_traces.pdf๐Ÿ“„ openthoughts_data_recipes.pdf๐Ÿ“„ os_world.pdf๐Ÿ“„ prompt_report_survey_prompt_engineering.pdf๐Ÿ“„ representation_engineering.pdf๐Ÿ“„ scalel_rl.pdf๐Ÿ“„ security_challenges_ai_agent_deployment.pdf๐Ÿ“„ survey_of_hallucination_nlg.pdf๐Ÿ“„ swe_bench_can_lms_resolve_github_issues.pdf๐Ÿ“„ swe_smith_scaling_data_for_swe_agents.pdf๐Ÿ“„ synthetic_data_gen_multistep_rl.pdf๐Ÿ“„ universal_transferable_adversarial_attacks.pdf

readings๏ผˆ1๏ผ‰

๐Ÿ“„ openai_practical_guide_to_building_agents.pdf

slides๏ผˆ11๏ผ‰

๐Ÿ“„ lecture01_course_intro_and_overview.pdf๐Ÿ“„ lecture02_models_prompting_rag.pdf๐Ÿ“„ lecture03_agentic_ai.pdf๐Ÿ“„ lecture04_recap_and_project_planning.pdf๐Ÿ“„ lecture05_allison_jia_systematic_agent_evals.pdf๐Ÿ“„ lecture06_ishita_mcp.pdf๐Ÿ“„ lecture06_mcp_yusuf_ozuysal.pdf๐Ÿ“„ lecture07_deep_dive_llms.pdf๐Ÿ“„ lecture08_data_curation_rl_for_agents.pdf๐Ÿ“„ lecture09_gepa_prompt_evolution.pdf๐Ÿ“„ lecture10_security_for_agents.pdf