mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-11-01 07:03:02 +00:00
ef6b0d74e1
- Add truncate_session_output in _file_io.py to render jsonl session lines as [speaker @ time] content before byte-budget truncation - Add read_step_format_session flag to ReadStep, honoring injected job kwargs (precedence) and YAML fallback - Inject read_step_format_session=True into BaseAgenticAnswerStep so agentic answer reads render session transcripts human-readably - Refine BEAM agentic_answer prompt: continue multi-angle search after preliminary answer, forbid fabrication/extrapolation - Update BEAM config to 1M variant and add sequential 100K-eval / 1M-build shell script - Refresh benchmark/results_md/beam.md with latest results
24 lines
1.1 KiB
YAML
24 lines
1.1 KiB
YAML
# BEAM evaluation configuration
|
|
# This file controls what/how to evaluate.
|
|
|
|
dataset:
|
|
beam_root: "benchmark/beam/dataset/BEAM" # BEAM dataset root
|
|
chat_size: "1M" # 100K | 500K | 1M | 10M (dataset variant)
|
|
case_ids: [] # empty = all cases; or ["1", "2", "3"]
|
|
start_index: 0 # first case index (for pagination)
|
|
num_items: 0 # 0 = all cases; >0 = limit
|
|
workspace_root: "benchmark/beam/workspaces/beam" # workspace root for case workspaces
|
|
|
|
evaluation:
|
|
num_workers: 20 # 0 = auto; 1 = sequential; >1 = parallel (per-case)
|
|
compress_session: false # true = compress session chunks in search_v2 (query-aware); false = no compression
|
|
|
|
reme:
|
|
config: "beam.yaml" # reme config (in reme/config/)
|
|
|
|
output:
|
|
dir: "benchmark/beam/results"
|
|
log_dir: "logs" # log directory (relative to project root)
|
|
log_prefix: "beam" # benchmark name used in log filenames
|
|
log_to_console: true
|
|
log_to_file: true
|