###### agent_config                                                               dataset_config

###main experiments
###gpt4o-mini
Long_context_agent_gpt-4o-mini.yaml                                      Accurate_Retrieval/Ruler/QA/Ruler_qa1_197k.yaml
Long_context_agent_gpt-4o-mini.yaml                                      Accurate_Retrieval/Ruler/QA/Ruler_qa2_421k.yaml
Long_context_agent_gpt-4o-mini.yaml                                      Accurate_Retrieval/LongMemEval/Longmemeval_s_star.yaml
Long_context_agent_gpt-4o-mini.yaml                                      Accurate_Retrieval/EventQA/Eventqa_full.yaml
Long_context_agent_gpt-4o-mini.yaml                                      Test_Time_Learning/ICL/ICL_banking77.yaml
Long_context_agent_gpt-4o-mini.yaml                                      Test_Time_Learning/ICL/ICL_clinic150.yaml
Long_context_agent_gpt-4o-mini.yaml                                      Test_Time_Learning/ICL/ICL_nlu.yaml
Long_context_agent_gpt-4o-mini.yaml                                      Test_Time_Learning/ICL/ICL_trec_coarse.yaml
Long_context_agent_gpt-4o-mini.yaml                                      Test_Time_Learning/ICL/ICL_trec_fine.yaml
Long_context_agent_gpt-4o-mini.yaml                                      Test_Time_Learning/Recsys/Recsys_redial_full.yaml
Long_context_agent_gpt-4o-mini.yaml                                      Long_Range_Understanding/InfBench_sum.yaml
Long_context_agent_gpt-4o-mini.yaml                                      Conflict_Resolution/Factconsolidation_sh_262k.yaml
Long_context_agent_gpt-4o-mini.yaml                                      Conflict_Resolution/Factconsolidation_mh_262k.yaml

###gpt-4o
Long_context_agent_gpt-4o.yaml                                           Accurate_Retrieval/Ruler/QA/Ruler_qa1_197k.yaml
Long_context_agent_gpt-4o.yaml                                           Accurate_Retrieval/Ruler/QA/Ruler_qa2_421k.yaml
Long_context_agent_gpt-4o.yaml                                           Accurate_Retrieval/LongMemEval/Longmemeval_s_star.yaml
Long_context_agent_gpt-4o.yaml                                           Accurate_Retrieval/EventQA/Eventqa_full.yaml
Long_context_agent_gpt-4o.yaml                                           Test_Time_Learning/ICL/ICL_banking77.yaml
Long_context_agent_gpt-4o.yaml                                           Test_Time_Learning/ICL/ICL_clinic150.yaml
Long_context_agent_gpt-4o.yaml                                           Test_Time_Learning/ICL/ICL_nlu.yaml
Long_context_agent_gpt-4o.yaml                                           Test_Time_Learning/ICL/ICL_trec_coarse.yaml
Long_context_agent_gpt-4o.yaml                                           Test_Time_Learning/ICL/ICL_trec_fine.yaml
Long_context_agent_gpt-4o.yaml                                           Test_Time_Learning/Recsys/Recsys_redial_full.yaml
Long_context_agent_gpt-4o.yaml                                           Long_Range_Understanding/InfBench_sum.yaml
Long_context_agent_gpt-4o.yaml                                           Conflict_Resolution/Factconsolidation_sh_262k.yaml
Long_context_agent_gpt-4o.yaml                                           Conflict_Resolution/Factconsolidation_mh_262k.yaml

###gpt-4.1-mini
Long_context_agent_gpt-4.1-mini.yaml                                     Accurate_Retrieval/Ruler/QA/Ruler_qa1_197k.yaml
Long_context_agent_gpt-4.1-mini.yaml                                     Accurate_Retrieval/Ruler/QA/Ruler_qa2_421k.yaml
Long_context_agent_gpt-4.1-mini.yaml                                     Accurate_Retrieval/LongMemEval/Longmemeval_s_star.yaml
Long_context_agent_gpt-4.1-mini.yaml                                     Accurate_Retrieval/EventQA/Eventqa_full.yaml
Long_context_agent_gpt-4.1-mini.yaml                                     Test_Time_Learning/ICL/ICL_banking77.yaml
Long_context_agent_gpt-4.1-mini.yaml                                     Test_Time_Learning/ICL/ICL_clinic150.yaml
Long_context_agent_gpt-4.1-mini.yaml                                     Test_Time_Learning/ICL/ICL_nlu.yaml
Long_context_agent_gpt-4.1-mini.yaml                                     Test_Time_Learning/ICL/ICL_trec_coarse.yaml
Long_context_agent_gpt-4.1-mini.yaml                                     Test_Time_Learning/ICL/ICL_trec_fine.yaml
Long_context_agent_gpt-4.1-mini.yaml                                     Test_Time_Learning/Recsys/Recsys_redial_full.yaml
Long_context_agent_gpt-4.1-mini.yaml                                     Long_Range_Understanding/InfBench_sum.yaml
Long_context_agent_gpt-4.1-mini.yaml                                     Conflict_Resolution/Factconsolidation_sh_262k.yaml
Long_context_agent_gpt-4.1-mini.yaml                                     Conflict_Resolution/Factconsolidation_mh_262k.yaml

###gemini-2.0-flash
Long_context_agent_gemini-2.0-flash.yaml                                Accurate_Retrieval/Ruler/QA/Ruler_qa1_197k.yaml
Long_context_agent_gemini-2.0-flash.yaml                                Accurate_Retrieval/Ruler/QA/Ruler_qa2_421k.yaml
Long_context_agent_gemini-2.0-flash.yaml                                Accurate_Retrieval/LongMemEval/Longmemeval_s_star.yaml
Long_context_agent_gemini-2.0-flash.yaml                                Accurate_Retrieval/EventQA/Eventqa_full.yaml
Long_context_agent_gemini-2.0-flash.yaml                                Test_Time_Learning/ICL/ICL_banking77.yaml
Long_context_agent_gemini-2.0-flash.yaml                                Test_Time_Learning/ICL/ICL_clinic150.yaml
Long_context_agent_gemini-2.0-flash.yaml                                Test_Time_Learning/ICL/ICL_nlu.yaml
Long_context_agent_gemini-2.0-flash.yaml                                Test_Time_Learning/ICL/ICL_trec_coarse.yaml
Long_context_agent_gemini-2.0-flash.yaml                                Test_Time_Learning/ICL/ICL_trec_fine.yaml
Long_context_agent_gemini-2.0-flash.yaml                                Test_Time_Learning/Recsys/Recsys_redial_full.yaml
Long_context_agent_gemini-2.0-flash.yaml                                Long_Range_Understanding/InfBench_sum.yaml
Long_context_agent_gemini-2.0-flash.yaml                                Conflict_Resolution/Factconsolidation_sh_262k.yaml
Long_context_agent_gemini-2.0-flash.yaml                                Conflict_Resolution/Factconsolidation_mh_262k.yaml


###claude-3-7-sonnet-20250219
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Accurate_Retrieval/Ruler/QA/Ruler_qa1_197k.yaml
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Accurate_Retrieval/Ruler/QA/Ruler_qa2_421k.yaml
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Accurate_Retrieval/LongMemEval/Longmemeval_s_star.yaml
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Accurate_Retrieval/EventQA/Eventqa_full.yaml
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Test_Time_Learning/ICL/ICL_banking77.yaml
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Test_Time_Learning/ICL/ICL_clinic150.yaml
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Test_Time_Learning/ICL/ICL_nlu.yaml
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Test_Time_Learning/ICL/ICL_trec_coarse.yaml
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Test_Time_Learning/ICL/ICL_trec_fine.yaml
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Test_Time_Learning/Recsys/Recsys_redial_full.yaml
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Long_Range_Understanding/InfBench_sum.yaml
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Conflict_Resolution/Factconsolidation_sh_262k.yaml
Long_context_agent_claude-3-7-sonnet-20250219.yaml                      Conflict_Resolution/Factconsolidation_mh_262k.yaml

###o4-mini
Long_context_agent_o4-mini.yaml                                         Conflict_Resolution/Factconsolidation_mh_6k.yaml       
Long_context_agent_o4-mini.yaml                                         Conflict_Resolution/Factconsolidation_sh_6k.yaml
Long_context_agent_o4-mini.yaml                                         Conflict_Resolution/Factconsolidation_mh_32k.yaml
Long_context_agent_o4-mini.yaml                                         Conflict_Resolution/Factconsolidation_sh_32k.yaml

Long_context_agent_gpt-4o-mini.yaml                                     Ruler_qa2_421k.yaml
Long_context_agent_gpt-4.1-mini.yaml                                    Ruler_qa2_421k.yaml
Long_context_agent_gpt-4o.yaml                                          Ruler_qa2_421k.yaml


Long_context_agent_gpt-4o-mini.yaml                                     ICL_banking77.yaml
Long_context_agent_gpt-4o-mini.yaml                                     ICL_clinic150.yaml
Long_context_agent_gpt-4o-mini.yaml                                     ICL_nlu.yaml
Long_context_agent_gpt-4o-mini.yaml                                     ICL_trec_coarse.yaml
Long_context_agent_gpt-4o-mini.yaml                                     ICL_trec_fine.yaml

Long_context_agent_gpt-4o.yaml                                          ICL_banking77.yaml
Long_context_agent_gpt-4o.yaml                                          ICL_clinic150.yaml
Long_context_agent_gpt-4o.yaml                                          ICL_nlu.yaml
Long_context_agent_gpt-4o.yaml                                          ICL_trec_coarse.yaml
Long_context_agent_gpt-4o.yaml                                          ICL_trec_fine.yaml