sa-buc bb7a436d51 feat: improve agentic answer prompt and update beam 100K results ... - Strengthen abstention rule: prohibit extrapolation from related but non-direct evidence - Add multi-angle search after preliminary answer to check for conflicting/supplementary/updated information - Add max-iteration fallback to 'Information not found' - Update beam.md with 100K results (agentscope 2.0.4.post1, from scratch) including per-type token consumption and memory construction stats - config.yaml: 100K dataset, 20 workers for BEAM evaluation - run.py: add memory construction token usage tracking (default agent) - Overall: 0.635 → 0.654 (+0.019), contradiction_resolution: 0.338 → 0.478 (+0.140), abstention: 0.500 → 0.525 (+0.025)		2026-08-05 01:48:54 +08:00
..
components	feat(evaluation): track job calls and agent token usage in benchmarks (#406)	2026-08-04 11:42:18 +08:00
config	feat: add CompressorStep and search_v2 dual-mode session compression	2026-08-04 15:30:38 +08:00
enumeration	feat: add mail component enum (#405)	2026-07-30 14:48:20 +08:00
schema	feat(evaluation): track job calls and agent token usage in benchmarks (#406)	2026-08-04 11:42:18 +08:00
steps	feat: improve agentic answer prompt and update beam 100K results	2026-08-05 01:48:54 +08:00
utils	feat(evaluation): track job calls and agent token usage in benchmarks (#406)	2026-08-04 11:42:18 +08:00
__init__.py	refactor(agent): unify agent subprocess env, sessions, skills, and MCP/service jobs (#382)	2026-07-20 23:52:14 +08:00
application.py	feat(benchmark): add LongMemEval golden answer validation (#335)	2026-07-13 21:26:27 +08:00
constants.py	feat(index): add file size limits and oversized file handling (#362)	2026-07-15 21:01:18 +08:00
reme.py	refactor(agent): unify agent subprocess env, sessions, skills, and MCP/service jobs (#382)	2026-07-20 23:52:14 +08:00