arxiv arXiv cs.CL · 1h ago · research

Mint-Agent introduces finance-native agentic foundation models

from English

Researchers present Mint-Agent, a family of finance-native agentic models designed to combine reliable execution with long-horizon research capabilities. The system is built on three pillars: a data engine for specialized tasks, the MintHarness environment for auditable evidence trails, and a training recipe combining SFT, OPD, and RLVR.

Two flagship models are released: Mint-Cu (9B) and Mint-Ag (27B).
Mint-Ag achieves 98.33% on RFC-Bench, surpassing GPT-5.6-Sol and Claude-Opus-4.8.
Mint-Cu reaches 69.86% on FinSearchComp T2, outperforming Agents-A1-35B and Nex-N2-mini.
Mint-Ag scores 76.00% and 60.49% on FinanceAgentBench v1.1 and v2, respectively.

These results establish a path toward trustworthy financial intelligence by jointly engineering domain expertise, long-horizon execution, and auditable evidence.

Importance 2/3 New harness with differentiators arXiv cs.CL DeepSeek AI agents Research paper

Read original

arxiv arXiv cs.LG · 4d ago · 26 views

Faraday 27B outperforms Claude Opus 4.8 and GPT-5.5 on paper replication tasks

Researchers have developed Replica, a scalable task space for paper replication, to address the need for reliable scientific knowledge. They post-trained Faraday, a 27B-parameter "AI Scientist" agent that uses coding agents as tools, to leverage this environment.

arxiv arXiv cs.AI · 4d ago · 20 views

Faraday 27B surpasses Claude Opus 4.8 and GPT-5.5 on paper replication tasks

Researchers have developed Replica, a scalable task space for paper replication, and introduced an auto-generated rubric-based judge to provide low-noise reward signals that align with human assessment.

arxiv arXiv cs.CL · 44d ago · 10 views

AutoMem automates learning of memory as a cognitive skill for LLMs

Researchers introduce AutoMem, a framework that treats memory management in large language models as a trainable skill rather than a static component. The system promotes file-system operations to first-class memory actions, allowing the model to autonomously decide how to encode, retrieve, and organize knowledge.

arxiv arXiv cs.CL · 49d ago · 13 views

Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent

Researchers introduce Agents-A1, a 35B Mixture-of-Experts model that achieves performance comparable to trillion-parameter models by scaling the agent horizon rather than parameter count. The approach focuses on extending long-horizon trajectories and unifying heterogeneous agent abilities through a specialized training infrastructure.

arxiv Moonshot AI (arXiv) · 259d ago · 2 views

DeepSeek-V3.2 introduces Sparse Attention and agentic synthesis, surpassing GPT-5

DeepSeek has released DeepSeek-V3.2, an open large language model that combines high computational efficiency with advanced reasoning capabilities. The release highlights three main technical advancements: a new sparse attention mechanism, a scalable reinforcement learning framework, and a pipeline for synthesizing agentic training data.