-
Reasoning Models Struggle to Control their Chains of Thought
Paper • 2603.05706 • Published • 40 -
FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use
Paper • 2603.08262 • Published • 27 -
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Paper • 2609.24972 • Published • 163 -
TradingAgents: Multi-Agents LLM Financial Trading Framework
Paper • 2412.20138 • Published • 164
Linhai Ma
lm2445
AI & ML interests
LLM, Information extraction, adversarial robustness, medical image analysis,
Recent Activity
updated a model 21 days ago
lm2445/PVminerLLM2-3.5-9b published a model 21 days ago
lm2445/PVminerLLM2-3.5-9bOrganizations
None yet
-
Reasoning Models Struggle to Control their Chains of Thought
Paper • 2603.05706 • Published • 40 -
FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use
Paper • 2603.08262 • Published • 27 -
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses
Paper • 2609.24972 • Published • 163 -
TradingAgents: Multi-Agents LLM Financial Trading Framework
Paper • 2412.20138 • Published • 164
models 35
lm2445/PVminerLLM2-3.5-9b
9B • Updated • 34
lm2445/PVminerLLM2-27b
27B • Updated • 49
lm2445/PVminerLLM2_70B
71B • Updated • 11
lm2445/PVminerLLM2_1.5B
2B • Updated • 17
lm2445/PVminerLLM_10epoch_sft_qwen2.5_1.5b
2B • Updated • 6
lm2445/PVminerLLM_10epoch_sft_llama3.1_8B
8B • Updated • 6
lm2445/PVminerLLM_10epoch_sft_llama3.2_3B
3B • Updated • 6
lm2445/PVminerLLM_10epoch_sft_llama3.3_70B
71B • Updated • 4
lm2445/PVminerLLM2_8B
8B • Updated • 4
lm2445/PVminerLLM2_3B
3B • Updated • 8
datasets 7
lm2445/DeRef
Viewer • Updated • 8.29k • 187
lm2445/CodeEps_FHS
Viewer • Updated • 3.14k • 67
lm2445/FinTagging1000_Grounding
Viewer • Updated • 2.51k • 31
lm2445/FinTagging1000_text
Viewer • Updated • 385 • 29
lm2445/FinTagging1000_table
Viewer • Updated • 574 • 50
lm2445/FinTagging1000_ER
Viewer • Updated • 1k • 22
lm2445/FinTagging_1000
Viewer • Updated • 1k • 42