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
..
benchmark	feat: improve agentic answer prompt and update beam 100K results	2026-08-05 01:48:54 +08:00
common	feat(core): add shell execution and runtime memory status (#344)	2026-07-14 16:31:41 +08:00
cookbook	refactor(auto_fin): normalize data models and selection logic across agents (#396)	2026-07-27 20:15:27 +08:00
evolve	refactor(compress): relax session compression to lenient format-preserving strategy and update LME results	2026-08-04 15:31:23 +08:00
file_io	feat(auto_memory): add source line-number markers for note traceability	2026-08-04 15:28:01 +08:00
index	refactor(compress): relax session compression to lenient format-preserving strategy and update LME results	2026-08-04 15:31:23 +08:00
transfer	feat(benchmark): add lme benchmark steps (#326)	2026-07-07 18:53:39 +09:00
__init__.py	feat: add daily paper cookbook and DingTalk agent integration (#385)	2026-07-22 19:17:01 +08:00
base_step.py	feat: add Auto Fin cookbook and managed outbound proxy support (#392)	2026-07-25 18:09:39 +08:00