✨Beyond Static Tools: Test-Time Tool Evolution for Scientific Reasoning
📝 Summary:
Existing AI agents for science struggle with static tool libraries. This paper introduces Test-Time Tool Evolution TTE, a new method allowing agents to dynamically create, verify, and evolve tools during inference. TTE achieves state-of-the-art performance and adapts tools across domains.
🔹 Publication Date: Published on Jan 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.07641
• PDF: https://arxiv.org/pdf/2601.07641
• Github: https://github.com/lujiaxuan0520/Test-Time-Tool-Evol
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AI #ScientificReasoning #ToolEvolution #AgentAI #AIResearch
📝 Summary:
Existing AI agents for science struggle with static tool libraries. This paper introduces Test-Time Tool Evolution TTE, a new method allowing agents to dynamically create, verify, and evolve tools during inference. TTE achieves state-of-the-art performance and adapts tools across domains.
🔹 Publication Date: Published on Jan 12
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.07641
• PDF: https://arxiv.org/pdf/2601.07641
• Github: https://github.com/lujiaxuan0520/Test-Time-Tool-Evol
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AI #ScientificReasoning #ToolEvolution #AgentAI #AIResearch
✨LongCat-Flash-Thinking-2601 Technical Report
📝 Summary:
LongCat-Flash-Thinking-2601 is a 560B MoE reasoning model that achieves state-of-the-art performance on agentic benchmarks. Its capabilities stem from a unified training framework, robust tool interaction, and a Heavy Thinking mode for complex reasoning.
🔹 Publication Date: Published on Jan 23
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.16725
• PDF: https://arxiv.org/pdf/2601.16725
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#MoE #ReasoningModels #AgentAI #LLM #AI
📝 Summary:
LongCat-Flash-Thinking-2601 is a 560B MoE reasoning model that achieves state-of-the-art performance on agentic benchmarks. Its capabilities stem from a unified training framework, robust tool interaction, and a Heavy Thinking mode for complex reasoning.
🔹 Publication Date: Published on Jan 23
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.16725
• PDF: https://arxiv.org/pdf/2601.16725
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#MoE #ReasoningModels #AgentAI #LLM #AI
✨DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints
📝 Summary:
DeepPlanning is a new benchmark for long-horizon agent planning, addressing the lack of global optimization and fine-grained local constraints in current LLM assessments. It features complex real-world tasks where even frontier LLMs struggle, highlighting the need for explicit reasoning and paral...
🔹 Publication Date: Published on Jan 26
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.18137
• PDF: https://arxiv.org/pdf/2601.18137
✨ Datasets citing this paper:
• https://huggingface.co/datasets/Qwen/DeepPlanning
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AIPlanning #LLMs #AgentAI #Benchmarking #DeepLearning
📝 Summary:
DeepPlanning is a new benchmark for long-horizon agent planning, addressing the lack of global optimization and fine-grained local constraints in current LLM assessments. It features complex real-world tasks where even frontier LLMs struggle, highlighting the need for explicit reasoning and paral...
🔹 Publication Date: Published on Jan 26
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2601.18137
• PDF: https://arxiv.org/pdf/2601.18137
✨ Datasets citing this paper:
• https://huggingface.co/datasets/Qwen/DeepPlanning
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AIPlanning #LLMs #AgentAI #Benchmarking #DeepLearning
✨Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
📝 Summary:
Trace2Skill generates transferable LLM agent skills by analyzing diverse execution traces in parallel and consolidating them via inductive reasoning. This framework significantly improves performance, transfers across LLM scales, and generalizes to new settings without model updates.
🔹 Publication Date: Published on Mar 26
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.25158
• PDF: https://arxiv.org/pdf/2603.25158
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#LLM #AgentAI #TransferLearning #MachineLearning #AIResearch
📝 Summary:
Trace2Skill generates transferable LLM agent skills by analyzing diverse execution traces in parallel and consolidating them via inductive reasoning. This framework significantly improves performance, transfers across LLM scales, and generalizes to new settings without model updates.
🔹 Publication Date: Published on Mar 26
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.25158
• PDF: https://arxiv.org/pdf/2603.25158
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#LLM #AgentAI #TransferLearning #MachineLearning #AIResearch
✨AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
📝 Summary:
Computer-use agents pose unique safety risks as harm can emerge from sequences of individually benign actions. AgentHazard is a benchmark with 2,653 instances to evaluate this. Experiments reveal current systems are highly vulnerable, showing model alignment alone doesnt ensure agent safety.
🔹 Publication Date: Published on Apr 3
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02947
• PDF: https://arxiv.org/pdf/2604.02947
• Project Page: https://yunhao-feng.github.io/AgentHazard/
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AISafety #AgentAI #AIVulnerability #AIethics #AIbenchmark
📝 Summary:
Computer-use agents pose unique safety risks as harm can emerge from sequences of individually benign actions. AgentHazard is a benchmark with 2,653 instances to evaluate this. Experiments reveal current systems are highly vulnerable, showing model alignment alone doesnt ensure agent safety.
🔹 Publication Date: Published on Apr 3
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2604.02947
• PDF: https://arxiv.org/pdf/2604.02947
• Project Page: https://yunhao-feng.github.io/AgentHazard/
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#AISafety #AgentAI #AIVulnerability #AIethics #AIbenchmark
✨AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents
📝 Summary:
AgentSwing adaptively manages context for long-horizon web agents using parallel branching and lookahead routing. This state-aware framework outperforms static methods, reducing interactions while improving search efficiency and terminal precision.
🔹 Publication Date: Published on Mar 29
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.27490
• PDF: https://arxiv.org/pdf/2603.27490
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#WebAgents #AI #ContextManagement #ParallelComputing #AgentAI
📝 Summary:
AgentSwing adaptively manages context for long-horizon web agents using parallel branching and lookahead routing. This state-aware framework outperforms static methods, reducing interactions while improving search efficiency and terminal precision.
🔹 Publication Date: Published on Mar 29
🔹 Paper Links:
• arXiv Page: https://arxiv.org/abs/2603.27490
• PDF: https://arxiv.org/pdf/2603.27490
==================================
For more data science resources:
✓ https://xn--r1a.website/DataScienceT
#WebAgents #AI #ContextManagement #ParallelComputing #AgentAI
❤1