๐ CS329T ยท ๆฏๅฆ็ฆ
๐ ่ทฏๅพไธ ยท Agentic
CS329T ยท Trustworthy ML / Agentic AI
ไธป่ฎฒ๏ผAnupam DattaใJohn Mitchell ๏ฝ Autumn 2025 ๏ฝ ๅฎ็ฝ๏ผ
https://web.stanford.edu/class/cs329t
๐ฌ ๆ ๅฎๆนๅฝๆญ๏ผ่ฎฒไน+่ฎบๆๅทฒๆฌๅฐๅ
๐ ๆๆ็ฎๅฝ
๐ ่ฏพ็จๅฎ็ฝ
ๆฌๅฐๆๆ
homeworks๏ผ1๏ผ
๐ CS329T_HW1_Fall2025.pdf
papers๏ผ22๏ผ
๐ agent_as_a_judge.pdf
๐ agent_gpa_goal_plan_action_alignment.pdf
๐ agentharm_benchmark_harmfulness_llm_agents.pdf
๐ are_scaling_up_agent_environments.pdf
๐ dapo_open_source_llm_rl_at_scale.pdf
๐ eval_benchmark_llm_agents_survey.pdf
๐ gepa_reflective_prompt_evolution.pdf
๐ grounding_and_evaluation_llms.pdf
๐ harmbench_standardized_eval_red_teaming.pdf
๐ improving_alignment_robustness_circuit_breakers.pdf
๐ naturalthoughts_reasoning_traces.pdf
๐ openthoughts_data_recipes.pdf
๐ os_world.pdf
๐ prompt_report_survey_prompt_engineering.pdf
๐ representation_engineering.pdf
๐ scalel_rl.pdf
๐ security_challenges_ai_agent_deployment.pdf
๐ survey_of_hallucination_nlg.pdf
๐ swe_bench_can_lms_resolve_github_issues.pdf
๐ swe_smith_scaling_data_for_swe_agents.pdf
๐ synthetic_data_gen_multistep_rl.pdf
๐ universal_transferable_adversarial_attacks.pdf
readings๏ผ1๏ผ
๐ openai_practical_guide_to_building_agents.pdf
slides๏ผ11๏ผ
๐ lecture01_course_intro_and_overview.pdf
๐ lecture02_models_prompting_rag.pdf
๐ lecture03_agentic_ai.pdf
๐ lecture04_recap_and_project_planning.pdf
๐ lecture05_allison_jia_systematic_agent_evals.pdf
๐ lecture06_ishita_mcp.pdf
๐ lecture06_mcp_yusuf_ozuysal.pdf
๐ lecture07_deep_dive_llms.pdf
๐ lecture08_data_curation_rl_for_agents.pdf
๐ lecture09_gepa_prompt_evolution.pdf
๐ lecture10_security_for_agents.pdf