File tree Expand file tree Collapse file tree 5 files changed +23
-4
lines changed Expand file tree Collapse file tree 5 files changed +23
-4
lines changed Original file line number Diff line number Diff line change 55
66class MainAgentPromptBoxedDeepSeek (BaseAgentPrompt ):
77 """
8- Adapted from MainAgentPromptBoxedAnswer. Since the tool-use is DeepSeek format, we remove the <use_mcp_tool> tags and its corresponding format instructions.
8+ Adapted from MainAgentPromptBoxedAnswer. Since the tool-use is DeepSeek format, we remove the <use_mcp_tool> tags and its corresponding format instructions.
99 """
1010
1111 def __init__ (self , * args , ** kwargs ):
Original file line number Diff line number Diff line change @@ -377,4 +377,4 @@ def generate_system_prompt_with_mcp_tools(
377377
378378"""
379379
380- return prompt
380+ return prompt
Original file line number Diff line number Diff line change @@ -272,6 +272,15 @@ Welcome to our comprehensive resource collection for AI agents. This page curate
272272** P084** - HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities
273273 - [ :material-file-document: Paper] ( https://arxiv.org/abs/2510.12200 )
274274
275+ ** P085** - Deep Research Brings Deeper Harm
276+ - [ :material-file-document: Paper] ( https://arxiv.org/abs/2510.11851 )
277+
278+
279+ A\textsuperscript{2}FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning, https://arxiv.org/abs/2510.12838
280+
281+ DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping, https://arxiv.org/abs/2510.12979
282+
283+
275284
276285---
277286
@@ -400,6 +409,9 @@ Welcome to our comprehensive resource collection for AI agents. This page curate
400409** E031** - A Comprehensive Survey on Benchmarks and Solutions in Software Engineering of LLM-Empowered Agentic System
401410 - [ :material-file-document: Paper] ( https://arxiv.org/abs/2510.09721 )
402411
412+ ** E032** - Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
413+ - [ :material-file-document: Paper] ( https://arxiv.org/abs/2510.11977 )
414+
403415
404416---
405417
Original file line number Diff line number Diff line change 1818
1919 ** Oct 2025** -
2020
21-
21+ **Week 2**
22+
23+ - 🌐 Added support for BrowseComp-ZH (Chinese) evaluation benchmark [#88](https://github.com/MiroMindAI/MiroFlow/pull/88)
24+ - 🤖 Added support for DeepSeek V3.1 with OpenRouter and tool call format [#86](https://github.com/MiroMindAI/MiroFlow/pull/86)
25+ - 🚶 Added support for WebWalkerQA dataset evaluation [#84](https://github.com/MiroMindAI/MiroFlow/pull/84)
26+ - 📖 Updated documentation for reading and audio tools [#83](https://github.com/MiroMindAI/MiroFlow/pull/83)
2227 - 📝 Added support for HLE-Text evaluation benchmark [#81](https://github.com/MiroMindAI/MiroFlow/pull/81)
2328 - 🧠 Added support for HLE (Humanity's Last Exam) benchmark [#79](https://github.com/MiroMindAI/MiroFlow/pull/79)
2429 - 🌐 Added support for BrowseComp-EN evaluation benchmark [#78](https://github.com/MiroMindAI/MiroFlow/pull/78)
2530 - 🔌 Added support for MiroAPI integration [#76](https://github.com/MiroMindAI/MiroFlow/pull/76)
2631
32+ **Week 1**
33+
2734 - 📊 Added support for FinSearchComp evaluation benchmark [#51](https://github.com/MiroMindAI/MiroFlow/pull/51)
2835 - 🔍 Added support for XBench-DS (Deep Search) evaluation [#47](https://github.com/MiroMindAI/MiroFlow/pull/47)
2936 - 🧠 Updated o3 hints and summary to more models [#58](https://github.com/MiroMindAI/MiroFlow/pull/58)
Original file line number Diff line number Diff line change @@ -97,7 +97,7 @@ async def _create_message(
9797 processed_messages = messages_copy
9898 else :
9999 processed_messages = self ._apply_cache_control (messages_copy )
100-
100+
101101 # For deepseek, we need to explicitly specify the tool list and add it to the messages
102102 tool_list = await self .convert_tool_definition_to_tool_call (tools_definitions )
103103
You can’t perform that action at this time.
0 commit comments