Tootfinder

Tool-integrated Reinforcement Learning for Repo Deep Search
Zexiong Ma, Chao Peng, Qunhong Zeng, Pengfei Gao, Yanzhen Zou, Bing Xie
https://arxiv.org/abs/2508.03012 https://

Tool-integrated Reinforcement Learning for Repo Deep Search
Issue localization, the process of identifying code locations that need modification to resolve software issues, is a critical yet challenging task in software development. The semantic gap between natural language issue descriptions and faulty code requires complex multi-hop reasoning through code dependencies. Existing LLM-based agents attempt to address this by integrating repository retrieval tools. However, this transforms issue localization into a demanding task we call Repo Deep Search, …

Oxford-based Ultromics, which has developed the first FDA-cleared, Medicare-reimbursed AI tools for cardiology diagnostics, raised a $55M Series C (Tamara Djurickovic/Tech.eu)
https://tech.eu/2025/07/31/ultromics-raises-55m-series-c-to-sca…

Ultromics raises $55M Series C to scale AI-driven heart failure detection
Oxford-based Ultromics, a pioneer in AI-driven cardiology diagnostics solutions, has raised $55 million through its Series C funding round.  Ultromics has developed the first FDA-cleared, Medicare-reimbursed AI technology designed to help clinicians detect Heart Failure with Preserved Ejection Fraction (HFpEF) and cardiac amyloidosis, two of the most difficult-to-diagnose forms of heart failure. Built on years of clinical research and analysis of hundreds of thousands of echocardiograms, the …

AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning
Yifan Wei, Xiaoyan Yu, Yixuan Weng, Tengfei Pan, Angsheng Li, Li Du
https://arxiv.org/abs/2507.21836 ht…

AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning
Large Language Models (LLMs), when enhanced through reasoning-oriented post-training, evolve into powerful Large Reasoning Models (LRMs). Tool-Integrated Reasoning (TIR) further extends their capabilities by incorporating external tools, but existing methods often rely on rigid, predefined tool-use patterns that risk degrading core language competence. Inspired by the human ability to adaptively select tools, we introduce AutoTIR, a reinforcement learning framework that enables LLMs to autonomo…

This https://arxiv.org/abs/2504.14870 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

Acting Less is Reasoning More! Teaching Model to Act Efficiently
Tool-integrated reasoning (TIR) augments large language models (LLMs) with the ability to invoke external tools during long-form reasoning, such as search engines and code interpreters, to solve tasks beyond the capabilities of internal reasoning. While reinforcement learning (RL) has shown promise in training such agents, most of existing approaches typically optimize only for final correctness without considering the efficiency or necessity of external tool use. This often leads to excessive …

"Scientists’ Letter Urges Brazil’s President Lula to Reject New Amazon and Offshore Drilling"
#Brazil #AmazonRainforest #Environment

Scientists’ Letter Urges Brazil’s President Lula to Reject New Amazon and Offshore Drilling - Inside Climate News
The urgent message was delivered to Brazilian officials during annual U.N. climate talks in Bonn, Germany, and includes new warnings about an Amazon rainforest tipping point.

Jeszcze nie tak dawno mogliśmy zobaczyć prehistoryczne rysunki w jaskiniach w Hiszpanii, a dziś rano byliśmy w muzeum w Alta, gdzie nad dawnym brzegiem fiordu znajdują się ryciny i malowidła naskalne.

Rysunki te mają od 7000 do 4000 lat, część się dobrze zachowała pod torfem, a niektóre wyblakły zostawiając tylko wyryte w skale kontury.

"Odkryto" je w latach 60 i 70 ubiegłego wieku. Przedstawiają sceny z polowań, rybołówstwa, wypasu reniferów i codziennego życia. Ogólnie…

A Digital Twin Framework for Generation-IV Reactors with Reinforcement Learning-Enabled Health-Aware Supervisory Control
Jasmin Y. Lim, Dimitrios Pylorof, Humberto E. Garcia, Karthik Duraisamy
https://arxiv.org/abs/2506.17258

A Digital Twin Framework for Generation-IV Reactors with Reinforcement Learning-Enabled Health-Aware Supervisory Control
Generation IV (Gen-IV) nuclear power plants are envisioned to replace the current reactor fleet, bringing improvements in performance, safety, reliability, and sustainability. However, large cost investments currently inhibit the deployment of these advanced reactor concepts. Digital twins bridge real-world systems with digital tools to reduce costs, enhance decision-making, and boost operational efficiency. In this work, a digital twin framework is designed to operate the Gen-IV Fluoride-salt-…

Filters of Identity: AR Beauty and the Algorithmic Politics of the Digital Body
Miriam Doh, Corinna Canali, Nuria Oliver
https://arxiv.org/abs/2506.19611 h…

Filters of Identity: AR Beauty and the Algorithmic Politics of the Digital Body
This position paper situates AR beauty filters within the broader debate on Body Politics in HCI. We argue that these filters are not neutral tools but technologies of governance that reinforce racialized, gendered, and ableist beauty standards. Through naming conventions, algorithmic bias, and platform governance, they impose aesthetic norms while concealing their influence. To address these challenges, we advocate for transparency-driven interventions and a critical rethinking of algorithmic …

Harnessing the Power of Reinforcement Learning for Adaptive MCMC
Congye Wang, Matthew A. Fisher, Heishiro Kanagawa, Wilson Chen, Chris. J. Oates
https://arxiv.org/abs/2507.00671

Harnessing the Power of Reinforcement Learning for Adaptive MCMC
Sampling algorithms drive probabilistic machine learning, and recent years have seen an explosion in the diversity of tools for this task. However, the increasing sophistication of sampling algorithms is correlated with an increase in the tuning burden. There is now a greater need than ever to treat the tuning of samplers as a learning task in its own right. In a conceptual breakthrough, Wang et al (2025) formulated Metropolis-Hastings as a Markov decision process, opening up the possibility fo…

Eliciting Reasoning in Language Models with Cognitive Tools
Brown Ebouky, Andrea Bartezzaghi, Mattia Rigotti
https://arxiv.org/abs/2506.12115 https://

Eliciting Reasoning in Language Models with Cognitive Tools
The recent advent of reasoning models like OpenAI's o1 was met with excited speculation by the AI community about the mechanisms underlying these capabilities in closed models, followed by a rush of replication efforts, particularly from the open source community. These speculations were largely settled by the demonstration from DeepSeek-R1 that chains-of-thought and reinforcement learning (RL) can effectively replicate reasoning on top of base LLMs. However, it remains valuable to explore alte…