6 Commits (1a18cd7bfdffe9971714887012b7a9b4e7725e81)

Author SHA1 Message Date
thinhlpg 77f121662f test: add tests for reward_retry function scenarios
1 month ago
thinhlpg 3081d6e36b test: added tests for new reward functions: search strategy and search diversity
1 month ago
thinhlpg d0e6068055 fix: strengthen reward correctness logic to handle final message is not asnwer form assistant. Also update logs for reward functions for better debug
1 month ago
thinhlpg 1bd609dfae test: enhance reward correctness tests with validation logic
1 month ago
thinhlpg 133cb1ab90 test: add Qwen tokenizer adapter tests
1 month ago
thinhlpg 3910ef343a test: add unit tests for agent, reward functions, and tokenizer adapters
1 month ago