caesar-agent 0.3.14__tar.gz → 0.4.28__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/LICENSE +26 -0
- caesar_agent-0.4.28/PKG-INFO +410 -0
- caesar_agent-0.4.28/README.md +335 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/analysis/llm_as_judge.py +1 -1
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/analysis/transfer_configs.py +1 -1
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/artifact_synthesis.py +370 -126
- caesar_agent-0.4.28/caesar/arxiv_explorer.py +394 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/brave_search.py +58 -7
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/caesar_agent.py +74 -39
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/caesar_config.py +111 -8
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_agi/improve_transformer.yaml +2 -2
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_agi/intelligence_bottleneck.yaml +2 -2
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_agi/single_agent_agi.yaml +2 -2
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_agi/solve_arcagi.yaml +2 -2
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_creative/constrained_creativity.yaml +3 -3
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_creative/counterfactual_reasoning.yaml +3 -3
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_creative/crossdomain_synthesis.yaml +3 -3
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_creative/meta_creativity.yaml +3 -3
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_creative/openended_creativity.yaml +3 -3
- caesar_agent-0.4.28/caesar/config/config_preset/arxiv.yaml +81 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_preset/mini.yaml +3 -3
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_preset/nano.yaml +2 -2
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_preset/regular.yaml +9 -5
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_test/single_agent_test.yaml +2 -2
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_wikipedia/single_agent_ai.yaml +2 -2
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_wikipedia/single_agent_evo.yaml +2 -2
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_wikipedia/single_agent_sci.yaml +2 -2
- caesar_agent-0.4.28/caesar/config/llm_as_judge/llm_prompts/nus_rubric_4pt_api.txt +87 -0
- caesar_agent-0.4.28/caesar/image_generator.py +1720 -0
- caesar_agent-0.4.28/caesar/query_result/1_10_all_agent_answers/nus_rubric_study/analysis/agg5.py +27 -0
- caesar_agent-0.4.28/caesar/query_result/1_10_all_agent_answers/nus_rubric_study/analysis/build5.py +42 -0
- caesar_agent-0.4.28/caesar/query_result/1_10_all_agent_answers/nus_rubric_study/analysis/cmp.py +46 -0
- caesar_agent-0.4.28/caesar/query_result/1_10_all_agent_answers/nus_rubric_study/analysis/compare.py +70 -0
- caesar_agent-0.4.28/caesar/query_result/1_10_all_agent_answers/nus_rubric_study/analysis/diag.py +55 -0
- caesar_agent-0.4.28/caesar/query_result/1_10_all_agent_answers/nus_rubric_study/analysis/summ.py +57 -0
- caesar_agent-0.4.28/caesar/query_result/1_10_all_agent_answers/nus_rubric_study/analysis/tally.py +38 -0
- caesar_agent-0.4.28/caesar/query_result/1_10_all_agent_answers/nus_rubric_study/analysis/v3an.py +57 -0
- caesar_agent-0.4.28/caesar/query_result/1_10_all_agent_answers/nus_rubric_study/analysis/v4an.py +57 -0
- caesar_agent-0.4.28/caesar/query_result/1_10_all_agent_answers/nus_rubric_study/analysis/v5an.py +72 -0
- caesar_agent-0.4.28/caesar/query_result/1_10_all_agent_answers/nus_rubric_study/analysis/why.py +39 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/run_agent.py +52 -5
- caesar_agent-0.4.28/caesar/semantic_scholar.py +207 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/web_explorer.py +165 -13
- caesar_agent-0.4.28/caesar_agent.egg-info/PKG-INFO +410 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar_agent.egg-info/SOURCES.txt +23 -1
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar_agent.egg-info/requires.txt +16 -8
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/pyproject.toml +21 -10
- caesar_agent-0.4.28/requirements.txt +64 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/agent_memory.py +39 -5
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/base_agent.py +28 -5
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/config.py +5 -2
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/kb_client.py +177 -106
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/kb_server.py +112 -26
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/llm_handler.py +237 -27
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/logger.py +17 -13
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/process.py +24 -2
- caesar_agent-0.4.28/test/test_arxiv_explorer.py +439 -0
- caesar_agent-0.4.28/test/test_arxiv_integration_manual.py +188 -0
- caesar_agent-0.4.28/test/test_kb_rerank_fallback.py +87 -0
- caesar_agent-0.4.28/test/test_public_mode_key.py +90 -0
- caesar_agent-0.4.28/test/test_reasoning_model_gating.py +72 -0
- caesar_agent-0.4.28/test/test_url_guard.py +261 -0
- caesar_agent-0.3.14/PKG-INFO +0 -278
- caesar_agent-0.3.14/README.md +0 -208
- caesar_agent-0.3.14/caesar_agent.egg-info/PKG-INFO +0 -278
- caesar_agent-0.3.14/requirements.txt +0 -45
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/NOTICE +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/__init__.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/analysis/judge_analysis.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/analysis/prepare_artifact.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/checkpoint.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_test/batch_test.jsonl +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/config_test/batch_test.yaml +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/custom_role/self_transcend_insights_v1.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/custom_role/self_transcend_insights_v2.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/custom_role/self_transcend_insights_v3.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/custom_role/self_transcend_insights_v4.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/custom_role/self_transcend_role_v1.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/custom_role/self_transcend_role_v2.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/custom_role/self_transcend_role_v3.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/agent_names/agent_names_all.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/agent_names/agent_names_caesar.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/human_prompts/human_eval_prompt.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/human_prompts/human_eval_prompt2.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/llm_prompts/eli5_prompt_long.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/llm_prompts/eli5_prompt_medium.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/llm_prompts/eli5_prompt_short.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/llm_prompts/judge_csv_prompt.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/llm_prompts/judge_summary_prompt.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/llm_prompts/nus_rubric_10pt_api.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/llm_prompts/nus_rubric_10pt_new.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/llm_prompts/nus_rubric_10pt_old.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/llm_prompts/query_prompt_deep.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/llm_prompts/query_prompt_shallow.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/queries/queries_n50.json +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/queries/queries_n50.jsonl +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/answer_bat_ca1.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/answer_bear_ca3.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/answer_cat_cam.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/answer_cow_cld.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/answer_dog_cls.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/answer_fox_ged.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/answer_lion_ges.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/answer_owl_gpd.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/answer_pig_gps.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/judge_claude.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/judge_gemini.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/judge_gpt.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar/config/llm_as_judge/templates/query.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar_agent.egg-info/dependency_links.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar_agent.egg-info/entry_points.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/caesar_agent.egg-info/top_level.txt +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/__init__.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action/__init__.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action/action.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action/advanced_reset_action.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action/edit_code_action.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action/edit_test_action.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action/exec_code_action.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action/priority_search_action.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action/reset_action.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action/revert_code_action.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action/save_kb_action.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action/tournament_search_action.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action/transition_action.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/action_selector.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/agent.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/agent_api.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/database.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/executor.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/fsm.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/fsm_selector.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/history.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/metadata.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/multi_agent.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/parsing.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/repository.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/rome/state.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/setup.cfg +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_compressor.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_database.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_evalplus_agent.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_executor.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_fsm.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_knowledge_base.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_llm_handler.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_logger.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_metadata.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_multi_agent.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_parsing.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_search.py +0 -0
- {caesar_agent-0.3.14 → caesar_agent-0.4.28}/test/test_single_agent.py +0 -0
|
@@ -1,3 +1,4 @@
|
|
|
1
|
+
|
|
1
2
|
Apache License
|
|
2
3
|
Version 2.0, January 2004
|
|
3
4
|
http://www.apache.org/licenses/
|
|
@@ -174,3 +175,28 @@
|
|
|
174
175
|
of your accepting any such warranty or additional liability.
|
|
175
176
|
|
|
176
177
|
END OF TERMS AND CONDITIONS
|
|
178
|
+
|
|
179
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
180
|
+
|
|
181
|
+
To apply the Apache License to your work, attach the following
|
|
182
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
183
|
+
replaced with your own identifying information. (Don't include
|
|
184
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
185
|
+
comment syntax for the file format. We also recommend that a
|
|
186
|
+
file or class name and description of purpose be included on the
|
|
187
|
+
same "printed page" as the copyright notice for easier
|
|
188
|
+
identification within third-party archives.
|
|
189
|
+
|
|
190
|
+
Copyright [yyyy] [name of copyright owner]
|
|
191
|
+
|
|
192
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
193
|
+
you may not use this file except in compliance with the License.
|
|
194
|
+
You may obtain a copy of the License at
|
|
195
|
+
|
|
196
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
197
|
+
|
|
198
|
+
Unless required by applicable law or agreed to in writing, software
|
|
199
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
200
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
201
|
+
See the License for the specific language governing permissions and
|
|
202
|
+
limitations under the License.
|
|
@@ -0,0 +1,410 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: caesar-agent
|
|
3
|
+
Version: 0.4.28
|
|
4
|
+
Summary: Caesar: autonomous AI research agent with graph-based deep web exploration and adversarial answer synthesis.
|
|
5
|
+
Author: Jason Liang, Elliot Meyerson, Risto Miikkulainen
|
|
6
|
+
Maintainer-email: Jason Liang <jasonzliang@utexas.edu>
|
|
7
|
+
License-Expression: Apache-2.0
|
|
8
|
+
Project-URL: Homepage, https://github.com/jasonzliang/caesar-agent
|
|
9
|
+
Project-URL: Repository, https://github.com/jasonzliang/caesar-agent
|
|
10
|
+
Project-URL: Issues, https://github.com/jasonzliang/caesar-agent/issues
|
|
11
|
+
Project-URL: Paper, https://arxiv.org/abs/2604.20855
|
|
12
|
+
Project-URL: Changelog, https://github.com/jasonzliang/caesar-agent/releases
|
|
13
|
+
Keywords: ai-agents,llm,rag,agentic-rag,agentic-ai,autonomous-agents,deep-research,research-agent,knowledge-graph,retrieval-augmented-generation,scientific-discovery,web-exploration,adversarial-refinement,llm-agents,openai,anthropic,chromadb,llama-index,ai-research
|
|
14
|
+
Classifier: Development Status :: 4 - Beta
|
|
15
|
+
Classifier: Intended Audience :: Developers
|
|
16
|
+
Classifier: Intended Audience :: Science/Research
|
|
17
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
18
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
19
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
20
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
21
|
+
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
22
|
+
Classifier: Topic :: Scientific/Engineering :: Information Analysis
|
|
23
|
+
Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
|
|
24
|
+
Requires-Python: <3.14,>=3.10
|
|
25
|
+
Description-Content-Type: text/markdown
|
|
26
|
+
License-File: LICENSE
|
|
27
|
+
License-File: NOTICE
|
|
28
|
+
Requires-Dist: litellm
|
|
29
|
+
Requires-Dist: networkx
|
|
30
|
+
Requires-Dist: numpy
|
|
31
|
+
Requires-Dist: openai
|
|
32
|
+
Requires-Dist: portalocker
|
|
33
|
+
Requires-Dist: psutil
|
|
34
|
+
Requires-Dist: pytest
|
|
35
|
+
Requires-Dist: scipy
|
|
36
|
+
Requires-Dist: tinydb
|
|
37
|
+
Requires-Dist: chromadb
|
|
38
|
+
Requires-Dist: llama-index
|
|
39
|
+
Requires-Dist: llama-index-vector-stores-chroma
|
|
40
|
+
Requires-Dist: llama-index-embeddings-openai
|
|
41
|
+
Requires-Dist: llama-index-llms-openai
|
|
42
|
+
Requires-Dist: pillow
|
|
43
|
+
Requires-Dist: mem0ai
|
|
44
|
+
Requires-Dist: anthropic
|
|
45
|
+
Requires-Dist: beautifulsoup4
|
|
46
|
+
Requires-Dist: curl_cffi>=0.16.3
|
|
47
|
+
Requires-Dist: ddgs
|
|
48
|
+
Requires-Dist: google-genai>=2.16.0
|
|
49
|
+
Requires-Dist: pygraphviz
|
|
50
|
+
Requires-Dist: pypdf
|
|
51
|
+
Requires-Dist: pyyaml>=6.0
|
|
52
|
+
Requires-Dist: tenacity
|
|
53
|
+
Requires-Dist: trafilatura>=2.1.0
|
|
54
|
+
Requires-Dist: fastapi
|
|
55
|
+
Requires-Dist: pytz
|
|
56
|
+
Requires-Dist: requests
|
|
57
|
+
Requires-Dist: rich
|
|
58
|
+
Requires-Dist: graphviz
|
|
59
|
+
Requires-Dist: tiktoken
|
|
60
|
+
Requires-Dist: xxhash
|
|
61
|
+
Provides-Extra: compress
|
|
62
|
+
Requires-Dist: llmlingua; extra == "compress"
|
|
63
|
+
Provides-Extra: benchmark
|
|
64
|
+
Requires-Dist: evalplus; extra == "benchmark"
|
|
65
|
+
Provides-Extra: dev
|
|
66
|
+
Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
|
|
67
|
+
Requires-Dist: black>=23.0.0; extra == "dev"
|
|
68
|
+
Requires-Dist: mypy>=1.7.0; extra == "dev"
|
|
69
|
+
Requires-Dist: ipython>=8.0.0; extra == "dev"
|
|
70
|
+
Provides-Extra: test
|
|
71
|
+
Requires-Dist: pytest>=7.4.0; extra == "test"
|
|
72
|
+
Requires-Dist: pytest-asyncio>=0.21.0; extra == "test"
|
|
73
|
+
Requires-Dist: pytest-xdist>=3.5.0; extra == "test"
|
|
74
|
+
Dynamic: license-file
|
|
75
|
+
|
|
76
|
+
<p align="center">
|
|
77
|
+
<img src="https://jasonzliang.github.io/caesar-agent/caesar.webp" alt="Caesar autonomous research agent architecture: Perceive-Think-Act exploration loop and adversarial artifact synthesis" width="720"/>
|
|
78
|
+
</p>
|
|
79
|
+
|
|
80
|
+
<h1 align="center">Caesar: Autonomous AI Research Agent</h1>
|
|
81
|
+
|
|
82
|
+
<p align="center">
|
|
83
|
+
<strong>The open-source alternative to ChatGPT Deep Research and Perplexity.</strong>
|
|
84
|
+
</p>
|
|
85
|
+
|
|
86
|
+
<p align="center">
|
|
87
|
+
<a href="https://caesar.evolution.ml"><strong>Try the live demo</strong></a>
|
|
88
|
+
·
|
|
89
|
+
<a href="https://jasonzliang.github.io/caesar-agent"><strong>Project home page</strong></a>
|
|
90
|
+
</p>
|
|
91
|
+
|
|
92
|
+
<p align="center">
|
|
93
|
+
<a href="https://caesar.evolution.ml"><img alt="Live demo" src="https://img.shields.io/badge/Live%20Demo-Try%20Caesar-2ea44f?logo=googlechrome&logoColor=white"></a>
|
|
94
|
+
<a href="https://arxiv.org/abs/2604.20855"><img alt="arXiv" src="https://img.shields.io/badge/arXiv-2604.20855-b31b1b?logo=arxiv&logoColor=white"></a>
|
|
95
|
+
<a href="https://www.researchgate.net/publication/402554537_Caesar_Deep_Agentic_Web_Exploration_for_Creative_Answer_Synthesis"><img alt="ResearchGate" src="https://img.shields.io/badge/ResearchGate-Caesar-00ccbb?logo=researchgate&logoColor=white"></a>
|
|
96
|
+
<a href="LICENSE"><img alt="License" src="https://img.shields.io/badge/License-Apache%202.0-blue?logo=apache&logoColor=white"></a>
|
|
97
|
+
<a href="https://github.com/jasonzliang/caesar-agent/commits/main"><img alt="Last commit" src="https://img.shields.io/github/last-commit/jasonzliang/caesar-agent?logo=github&logoColor=white&label=Last%20Commit&color=181717"></a>
|
|
98
|
+
</p>
|
|
99
|
+
|
|
100
|
+
**Caesar** is an autonomous AI research agent that navigates the web, reasons
|
|
101
|
+
over a dynamic knowledge graph, and synthesizes novel, grounded answers. In
|
|
102
|
+
blinded LLM-as-a-Judge creativity evaluations, Caesar scored **26.96 / 30** on
|
|
103
|
+
the headline full-answers configuration, beating the runner-up (Gemini 3 Deep
|
|
104
|
+
Research, 23.78) by **3.18 points** and outscoring GPT-5.2 Deep Research (15.74)
|
|
105
|
+
by over **11 points**. Cliff's δ effect sizes are uniformly large (**≥ 0.76**,
|
|
106
|
+
well above the 0.47 large-effect threshold), and the result is corroborated by
|
|
107
|
+
an independent 23-rater human study.
|
|
108
|
+
|
|
109
|
+
If you're looking for an **agentic RAG system that goes beyond retrieval**
|
|
110
|
+
(graph-based exploration, adversarial verification, and multi-draft synthesis),
|
|
111
|
+
this is it.
|
|
112
|
+
|
|
113
|
+
> 📄 **Read the paper:**
|
|
114
|
+
> [_Caesar: Deep Agentic Web Exploration for Creative Answer Synthesis_](https://arxiv.org/abs/2604.20855)
|
|
115
|
+
> (Liang, Meyerson, Miikkulainen, 2026 — **v3**, 8 May 2026) ·
|
|
116
|
+
> [DOI: 10.48550/arXiv.2604.20855](https://doi.org/10.48550/arXiv.2604.20855) ·
|
|
117
|
+
> [PDF](https://arxiv.org/pdf/2604.20855v3)
|
|
118
|
+
|
|
119
|
+
## Quickstart
|
|
120
|
+
|
|
121
|
+
**From PyPI:**
|
|
122
|
+
|
|
123
|
+
```bash
|
|
124
|
+
pip install caesar-agent
|
|
125
|
+
export OPENAI_API_KEY=your_key
|
|
126
|
+
caesar regular -q "your research question"
|
|
127
|
+
```
|
|
128
|
+
|
|
129
|
+
**From source:**
|
|
130
|
+
|
|
131
|
+
```bash
|
|
132
|
+
git clone https://github.com/jasonzliang/caesar-agent.git
|
|
133
|
+
cd caesar-agent && pip install -e .
|
|
134
|
+
export OPENAI_API_KEY=your_key
|
|
135
|
+
caesar regular -q "your research question"
|
|
136
|
+
```
|
|
137
|
+
|
|
138
|
+
**In a browser:**
|
|
139
|
+
|
|
140
|
+
```bash
|
|
141
|
+
cd web_server && ./launch.sh
|
|
142
|
+
# then open http://localhost:3000
|
|
143
|
+
```
|
|
144
|
+
|
|
145
|
+
The **[Caesar Web Server](web_server/README.md)** is a FastAPI + Next.js GUI
|
|
146
|
+
that submits runs, streams progress, and renders the live knowledge graph and
|
|
147
|
+
final artifact.
|
|
148
|
+
|
|
149
|
+
## Setup Notes
|
|
150
|
+
|
|
151
|
+
Both install paths give you the same `caesar` console script, so every command
|
|
152
|
+
in this README behaves identically whether you came from PyPI or from a
|
|
153
|
+
checkout. From a checkout you can also skip the script entirely and run
|
|
154
|
+
`python caesar/run_agent.py regular -q "..."` — that still needs the
|
|
155
|
+
dependencies (`pip install -r requirements.txt`), just not the package itself.
|
|
156
|
+
|
|
157
|
+
Everything else worth knowing before your first run:
|
|
158
|
+
|
|
159
|
+
- **Python** — 3.10 through 3.13
|
|
160
|
+
- **Presets** — `nano` (fast, ~$0.80), `mini` (balanced, ~$2), `regular` (deep,
|
|
161
|
+
~$5–$10). Cost scales with synthesis output tokens, so treat these as
|
|
162
|
+
order-of-magnitude rather than quotes.
|
|
163
|
+
- **API keys** — `OPENAI_API_KEY` alone is enough to run. Add
|
|
164
|
+
`ANTHROPIC_API_KEY` or `GOOGLE_API_KEY` to reach Claude and Gemini models, and
|
|
165
|
+
`BRAVE_API_KEY` for better web search — without it, search falls back to
|
|
166
|
+
DuckDuckGo.
|
|
167
|
+
- **Results** — `caesar/result/` from a source checkout, `~/.caesar/result/`
|
|
168
|
+
from a PyPI install. `CAESAR_RESULT_DIR` overrides both.
|
|
169
|
+
- **Custom configs** — drop a YAML in `~/.caesar/configs/` and call it by name
|
|
170
|
+
(`caesar my_preset -q "..."`). Bundled preset names take precedence, so avoid
|
|
171
|
+
naming yours `nano`, `mini`, or `regular`.
|
|
172
|
+
- **Going deeper** — the full env-var list, exploration modes, and synthesis
|
|
173
|
+
options are in the **[Caesar module docs](caesar/README.md)**.
|
|
174
|
+
|
|
175
|
+
## What It's Good For
|
|
176
|
+
|
|
177
|
+
Caesar shines on **open-ended, creative, cross-disciplinary** research, where
|
|
178
|
+
retrieval alone won't work:
|
|
179
|
+
|
|
180
|
+
- **Hypothesis generation**: novel cross-domain connections (e.g., bridging
|
|
181
|
+
materials science and biology)
|
|
182
|
+
- **Literature synthesis**: graph-grounded review that spots tensions and gaps
|
|
183
|
+
between papers
|
|
184
|
+
- **arXiv citation-graph review**: traverse the Semantic Scholar citation graph
|
|
185
|
+
of arXiv papers (papers as nodes, citations as edges) instead of the open web
|
|
186
|
+
(`caesar arxiv -q "..."`)
|
|
187
|
+
- **Competitive intelligence**: deep mapping of a technical or market landscape
|
|
188
|
+
- **Counterfactual & meta-creative reasoning**: "what if X was different?" style
|
|
189
|
+
inquiry
|
|
190
|
+
- **Novel solution ideation**: e.g., ARC-AGI–style problem exploration
|
|
191
|
+
|
|
192
|
+
It's **not** the right tool for quick factual lookups or latency-sensitive apps.
|
|
193
|
+
Caesar is designed for depth, not speed.
|
|
194
|
+
|
|
195
|
+
## Why Caesar?
|
|
196
|
+
|
|
197
|
+
Current deep-research agents (ChatGPT Deep Research, Perplexity, GPT Researcher,
|
|
198
|
+
Gemini Deep Research) optimize for **retrieval precision over a flat sequence of
|
|
199
|
+
documents**. They produce competent summaries but suffer from **navigational
|
|
200
|
+
amnesia**, fall into local minima, and generate derivative, consensus-driven
|
|
201
|
+
outputs.
|
|
202
|
+
|
|
203
|
+
Caesar is different:
|
|
204
|
+
|
|
205
|
+
| Design choice | Caesar | ChatGPT / Gemini Deep Research | Perplexity Research | GPT Researcher |
|
|
206
|
+
| --------------------------------------------------- | :----------------: | :----------------------------: | :-----------------: | :---------------------: |
|
|
207
|
+
| Persistent knowledge graph built during exploration | ✅ | not published | not published | ❌ |
|
|
208
|
+
| Adversarial refinement over its own drafts | ✅ | not published | 🟡 | 🟡 |
|
|
209
|
+
| Serialized graph and JSON run log you keep | ✅ | 🟡 | 🟡 | 🟡 |
|
|
210
|
+
| Runs on your own keys and hardware | ✅ | ❌ | ❌ | ✅ |
|
|
211
|
+
| Works with no setup and no API keys | ❌ | ✅ | ✅ | ❌ |
|
|
212
|
+
| Typical time to an answer | 10 min – 1.5 hrs | 5–30 min | under 3 min | 2–5 min |
|
|
213
|
+
| Browser and mobile access | ❌ | ✅ | ✅ | 🟡 |
|
|
214
|
+
| Maturity | research prototype | GA product | GA product | established open source |
|
|
215
|
+
|
|
216
|
+
<sub>Compared as of July 2026 against each product's then-current tier. **"Not
|
|
217
|
+
published"** means the vendor has not documented the mechanism, which is not the
|
|
218
|
+
same as its absence: these are closed systems and we can report only what they
|
|
219
|
+
disclose. ChatGPT and Deep Research are trademarks of OpenAI; Perplexity of
|
|
220
|
+
Perplexity AI; Gemini of Google.</sub>
|
|
221
|
+
|
|
222
|
+
## How It Works
|
|
223
|
+
|
|
224
|
+
Caesar operates in two cognitive phases:
|
|
225
|
+
|
|
226
|
+
### 1. Deep Web Exploration: stateful graph traversal
|
|
227
|
+
|
|
228
|
+
A recursive **Perceive–Think–Act** loop performs topological traversal of
|
|
229
|
+
information spaces. Rather than isolating summaries, Caesar generates
|
|
230
|
+
context-aware insights conditioned on the **local structure of the exploration
|
|
231
|
+
graph**, analyzing how new content builds upon or contradicts neighboring nodes.
|
|
232
|
+
A dynamic policy, informed by a vector knowledge base and episodic memory,
|
|
233
|
+
autonomously switches between depth-first expansion, strategic backtracking, and
|
|
234
|
+
targeted web search.
|
|
235
|
+
|
|
236
|
+
### 2. Adversarial Artifact Synthesis
|
|
237
|
+
|
|
238
|
+
Rather than a single-pass summary, Caesar runs as a recursive self-correction
|
|
239
|
+
environment. Between drafts the agent re-reads its own artifact and formulates a
|
|
240
|
+
refined, **orthogonal challenge** targeting narrative weaknesses, gaps and
|
|
241
|
+
contradictions in the current belief state. Drafts are produced recurrently,
|
|
242
|
+
each conditioned on the last, then merged — forcing the agent out of the
|
|
243
|
+
consensus basin that traps single-pass LLMs.
|
|
244
|
+
|
|
245
|
+
## Architectural Innovations
|
|
246
|
+
|
|
247
|
+
- **Domain-Specific Role Adaptation**: the agent rewrites its own system prompt
|
|
248
|
+
per task, overriding the safety-biased generic responses typical of RLHF
|
|
249
|
+
models.
|
|
250
|
+
- **Graph-Augmented Insight Generation**: insights are conditioned on the
|
|
251
|
+
exploration graph neighborhood, enabling online associative reasoning.
|
|
252
|
+
- **Knowledge-Guided Exploration Policy**: detects navigational stagnation via
|
|
253
|
+
episodic memory and forces backtracking.
|
|
254
|
+
- **Adversarial Query Refinement**: orthogonal queries push the agent out of
|
|
255
|
+
generic LLM consensus toward novel, grounded facts.
|
|
256
|
+
|
|
257
|
+
## Benchmark Results
|
|
258
|
+
|
|
259
|
+
Evaluated with a blinded **3-model LLM-as-a-Judge panel** (Claude Sonnet 4.5,
|
|
260
|
+
GPT-5.2, Gemini 3 Pro) across three creativity dimensions (**New**, **Useful**,
|
|
261
|
+
**Surprising**), scored 1–10 each. Headline configuration: full answers,
|
|
262
|
+
unconstrained length.
|
|
263
|
+
|
|
264
|
+
| Agent | New | Useful | Surprising | **Total** | Cliff's δ |
|
|
265
|
+
| ------------------------ | :------: | :------: | :--------: | :-------: | :-------: |
|
|
266
|
+
| **Caesar** | **9.11** | **8.87** | **8.98** | **26.96** | — |
|
|
267
|
+
| Gemini 3 Deep Research | 8.09 | 7.60 | 8.09 | 23.78 | 0.84 |
|
|
268
|
+
| Sonnet 4.5 Deep Research | 6.73 | 7.49 | 6.42 | 20.64 | 1.00 |
|
|
269
|
+
| GPT-5.2 Deep Research | 5.07 | 6.31 | 4.36 | 15.74 | 1.00 |
|
|
270
|
+
|
|
271
|
+
A **13–23% improvement over state-of-the-art deep research agents**, with Caesar
|
|
272
|
+
leading across all three output formats (Full, ELI5, ELI5-450W). Cliff's δ ≥
|
|
273
|
+
0.76 in every comparison (well above the 0.47 large-effect threshold); δ = 1.00
|
|
274
|
+
vs. GPT-5.2 Deep Research denotes strict dominance in every output format; vs.
|
|
275
|
+
Sonnet 4.5 Deep Research it is 1.00 on full answers and 0.76–0.96 on the ELI5
|
|
276
|
+
formats. The paper frames these results by magnitude of difference rather than
|
|
277
|
+
null-hypothesis testing: with n = 5 challenges per group, δ estimates stochastic
|
|
278
|
+
dominance and no p-values are reported.
|
|
279
|
+
|
|
280
|
+
**Compute-controlled comparison.** At a matched ~$5/challenge budget (T=250 with
|
|
281
|
+
GPT-5-mini), Caesar still wins: 26.16 vs. Gemini 3 Deep 24.37, Sonnet 4.5 Deep
|
|
282
|
+
21.00, GPT-5.2 Deep 16.16. The lead is not an artifact of larger compute.
|
|
283
|
+
|
|
284
|
+
**Human evaluation.** 23 raters preferred Caesar in 63 of 112 pairwise A/B
|
|
285
|
+
matchups vs. Gemini 3 Deep Research (56.25%, odds ratio 1.29), independently
|
|
286
|
+
corroborating the LLM-judge findings.
|
|
287
|
+
|
|
288
|
+
Ablations isolate what each component contributes. Removing the knowledge graph
|
|
289
|
+
costs δ = 0.52 (large), and restricting traversal to a single hop costs the
|
|
290
|
+
same; shallow exploration costs δ = 0.92 on total score. Adversarial refinement
|
|
291
|
+
is a trade rather than a uniform gain — it lifts Surprising (+1.76) and New at
|
|
292
|
+
the expense of Useful, and the generative merge recovers utility (7.04 → 8.28)
|
|
293
|
+
while keeping the discovered insights. See the
|
|
294
|
+
[paper](https://arxiv.org/abs/2604.20855) for full methodology,
|
|
295
|
+
per-output-format tables, exploration-budget ablation, and judge bias analysis.
|
|
296
|
+
|
|
297
|
+
## Example Output
|
|
298
|
+
|
|
299
|
+
After a run, Caesar writes a full artifact (abstract + body with citations) plus
|
|
300
|
+
a structured summary:
|
|
301
|
+
|
|
302
|
+
```json
|
|
303
|
+
{
|
|
304
|
+
"wall_time": 591.31,
|
|
305
|
+
"tokens_used": 109873,
|
|
306
|
+
"token_cost": 0.29,
|
|
307
|
+
"api_calls": 20,
|
|
308
|
+
"webpages_visited": 4,
|
|
309
|
+
"iterations_elapsed": 5,
|
|
310
|
+
"artifact_dir": "result/.../agent_CaesarExplorer.synthesis.04161850",
|
|
311
|
+
"num_drafts": 2,
|
|
312
|
+
"config_summary": { "...": "..." }
|
|
313
|
+
}
|
|
314
|
+
```
|
|
315
|
+
|
|
316
|
+
The `artifact_dir` contains one `.txt` per synthesis draft, a final merged
|
|
317
|
+
artifact, and a metadata file tracking sources cited in each draft. Knowledge
|
|
318
|
+
graphs are saved as compressed JSON checkpoints for reproducibility or post-hoc
|
|
319
|
+
analysis.
|
|
320
|
+
|
|
321
|
+
## Built on Rome
|
|
322
|
+
|
|
323
|
+
Caesar is built on **Rome**, a Finite State Machine framework for stateful AI
|
|
324
|
+
agents that provides the agent runtime (FSM lifecycles, action selection,
|
|
325
|
+
memory, LLM handling) that Caesar builds on, episodic memory, dynamic policy
|
|
326
|
+
routing, and verifiable code execution. See the
|
|
327
|
+
[Rome framework docs](rome/README.md) if you want to build your own agent on
|
|
328
|
+
top.
|
|
329
|
+
|
|
330
|
+
## Project Layout
|
|
331
|
+
|
|
332
|
+
```
|
|
333
|
+
caesar-agent/
|
|
334
|
+
├── caesar/ # Caesar agent (see caesar/README.md for full usage)
|
|
335
|
+
│ ├── caesar_agent.py
|
|
336
|
+
│ ├── artifact_synthesis.py
|
|
337
|
+
│ ├── run_agent.py
|
|
338
|
+
│ ├── config/ # YAML configs and creativity benchmarks
|
|
339
|
+
│ └── paper/ # Caesar paper (PDF)
|
|
340
|
+
├── rome/ # Rome framework (see rome/README.md): FSM, memory, LLM handlers, KB client
|
|
341
|
+
├── web_server/ # FastAPI + Next.js web GUI (see web_server/README.md)
|
|
342
|
+
└── web_app/ # Streamlit operator tools: human eval + graph explorer (see web_app/README.md)
|
|
343
|
+
```
|
|
344
|
+
|
|
345
|
+
## FAQ
|
|
346
|
+
|
|
347
|
+
**How is this different from LangGraph / CrewAI / AutoGen?** Those are
|
|
348
|
+
orchestration frameworks: they help you wire up agents. Rome is an opinionated
|
|
349
|
+
runtime for _how_ agents should reason (graph-structured exploration,
|
|
350
|
+
adversarial verification, episodic memory). Caesar is a concrete research agent
|
|
351
|
+
built on it.
|
|
352
|
+
|
|
353
|
+
**Do I need GPUs?** No. Caesar uses hosted LLM APIs (OpenAI, Anthropic). A local
|
|
354
|
+
ChromaDB instance handles the vector store. Runs on a laptop.
|
|
355
|
+
|
|
356
|
+
**Which models are supported?** OpenAI (GPT-5 family, o-series reasoning
|
|
357
|
+
models), Anthropic (Claude 4.5 / 4.6), Google (Gemini 3.x), and any
|
|
358
|
+
OpenAI-compatible endpoint. Model selection is per-subsystem (exploration,
|
|
359
|
+
synthesis, judging) via YAML config.
|
|
360
|
+
|
|
361
|
+
**How much does a typical run cost?** A 5-iteration exploration with
|
|
362
|
+
GPT-5.4-mini (`caesar/config/config_test/single_agent_test.yaml`) runs at
|
|
363
|
+
roughly $0.30 and 10 minutes. A 250-iteration deep run with the `regular` preset
|
|
364
|
+
(`gpt-5.6-terra` exploration, `gpt-5.6-sol` synthesis) is typically $5–$10.
|
|
365
|
+
|
|
366
|
+
**Can I reproduce the benchmarks?** Yes. Configs, judge rubrics, and evaluation
|
|
367
|
+
scripts are in `caesar/config/` and `caesar/analysis/`.
|
|
368
|
+
|
|
369
|
+
## Contributing & Community
|
|
370
|
+
|
|
371
|
+
- ⭐ **Star the repo** if Caesar is useful for your research
|
|
372
|
+
- 💬
|
|
373
|
+
**[Open a Discussion](https://github.com/jasonzliang/caesar-agent/discussions)**
|
|
374
|
+
for ideas, questions, or use cases
|
|
375
|
+
- 🐛 **[File an Issue](https://github.com/jasonzliang/caesar-agent/issues)** for
|
|
376
|
+
bugs or feature requests
|
|
377
|
+
- 🔧 **PRs welcome**, especially new exploration policies, synthesis strategies,
|
|
378
|
+
and benchmark domains
|
|
379
|
+
|
|
380
|
+
### Good places to start a fork
|
|
381
|
+
|
|
382
|
+
| Goal | Effort |
|
|
383
|
+
| ------------------------------------------------------------------ | :-----: |
|
|
384
|
+
| Adapt Caesar for your research domain (legal, biology, finance, …) | 1–2 hrs |
|
|
385
|
+
| Add a new web-search backend (Tavily, Exa, Serper, …) | 2–3 hrs |
|
|
386
|
+
| Experiment with multi-agent synthesis (ring or debate merge) | 4–6 hrs |
|
|
387
|
+
|
|
388
|
+
If you fork Caesar for your own work,
|
|
389
|
+
[open a Discussion](https://github.com/jasonzliang/caesar-agent/discussions) —
|
|
390
|
+
we'd love to see what you build.
|
|
391
|
+
|
|
392
|
+
## Citation
|
|
393
|
+
|
|
394
|
+
If you use Caesar in your research, please cite:
|
|
395
|
+
|
|
396
|
+
```bibtex
|
|
397
|
+
@misc{liang26caesar,
|
|
398
|
+
title={Caesar: Deep Agentic Web Exploration for Creative Answer Synthesis},
|
|
399
|
+
author={Jason Liang and Elliot Meyerson and Risto Miikkulainen},
|
|
400
|
+
year={2026},
|
|
401
|
+
eprint={2604.20855},
|
|
402
|
+
archivePrefix={arXiv},
|
|
403
|
+
primaryClass={cs.IR},
|
|
404
|
+
url={https://arxiv.org/abs/2604.20855},
|
|
405
|
+
}
|
|
406
|
+
```
|
|
407
|
+
|
|
408
|
+
## License
|
|
409
|
+
|
|
410
|
+
Apache License 2.0. See [LICENSE](LICENSE).
|