Update paper reference for Deep Researcher plugin

Changed all references from 'A Statistical Framework for Deep Researcher' to 'Deep Researcher with Test-Time Diffusion' and updated the associated arXiv URL in README, research_engine.py, and deep_research_plugin.py for accuracy and consistency.

Author: codelion

optillm/plugins/deep_research/README.md

@@ -2,19 +2,7 @@
 
 ## Overview
 
-The Deep Research plugin implements the **Test-Time Diffusion Deep Researcher (TTD-DR)** algorithm, a state-of-the-art approach for comprehensive research report generation. This implementation is based on the paper ["A Statistical Framework for Deep Researcher"](https://arxiv.org/html/2507.16075v1) and provides iterative, in-depth research capabilities for complex queries.
-
-## Paper Citation
-
-```bibtex
-@article{ttd_dr_2024,
-  title={A Statistical Framework for Deep Researcher},
-  author={[Paper Authors]},
-  journal={arXiv preprint arXiv:2507.16075},
-  year={2024},
-  url={https://arxiv.org/html/2507.16075v1}
-}
-```
+The Deep Research plugin implements the **Test-Time Diffusion Deep Researcher (TTD-DR)** algorithm, a state-of-the-art approach for comprehensive research report generation. This implementation is based on the paper ["Deep Researcher with Test-Time Diffusion"](https://arxiv.org/abs/2507.16075v1) and provides iterative, in-depth research capabilities for complex queries.
 
 ## Algorithm Overview
 
@@ -252,6 +240,3 @@ When contributing to the Deep Research plugin:
 4. Test with various query types and complexity levels
 5. Document any new configuration options
 
-## License
-
-This implementation follows the same license as the OptILLM project and includes proper attribution to the original TTD-DR paper authors.

optillm/plugins/deep_research/research_engine.py

@@ -2,7 +2,7 @@
 Deep Research Engine - Core Implementation
 
 This module implements the Test-Time Diffusion Deep Researcher (TTD-DR) algorithm
-as described in "A Statistical Framework for Deep Researcher" (https://arxiv.org/html/2507.16075v1).
+as described in "Deep Researcher with Test-Time Diffusion" (https://arxiv.org/abs/2507.16075v1).
 
 The TTD-DR approach treats research as a diffusion process with iterative refinement
 through denoising and retrieval, generating comprehensive research reports.
@@ -26,7 +26,7 @@ class DeepResearcher:
     This class implements the paper's approach of treating research as a diffusion process
     with iterative refinement through denoising and retrieval.
     
-    Based on: https://arxiv.org/html/2507.16075v1
+    Based on: https://arxiv.org/abs/2507.16075v1
     """
 
     def __init__(self, client, model: str, max_iterations: int = 5, max_sources: int = 10):

optillm/plugins/deep_research_plugin.py

@@ -2,9 +2,9 @@
 Deep Research Plugin - OptILLM Plugin Interface
 
 This plugin implements the Test-Time Diffusion Deep Researcher (TTD-DR) algorithm
-from the paper "A Statistical Framework for Deep Researcher".
+from the paper "Deep Researcher with Test-Time Diffusion".
 
-Paper: https://arxiv.org/html/2507.16075v1
+Paper: https://arxiv.org/abs/2507.16075v1
 
 The plugin orchestrates web search, URL fetching, and memory synthesis to provide
 comprehensive research responses using an iterative refinement approach.
@@ -23,8 +23,8 @@ def run(system_prompt: str, initial_query: str, client, model: str, request_conf
     This plugin orchestrates web search, URL fetching, and memory synthesis to provide
     comprehensive research responses using an iterative refinement approach.
     
-    Based on: "A Statistical Framework for Deep Researcher" 
-    https://arxiv.org/html/2507.16075v1
+    Based on: "Deep Researcher with Test-Time Diffusion" 
+    https://arxiv.org/abs/2507.16075v1
     
     Args:
         system_prompt: System prompt for the conversation