Related papers: Tool Building as a Path to "Superintelligence"

Tool Building as a Path to "Superintelligence"

URL: http://arxiv.org/abs/2602.21061v1
Date: Tue, 24 Feb 2026 16:22:10 GMT
Title: Tool Building as a Path to "Superintelligence"
Authors: David Koplow, Tomer Galanti, Tomaso Poggio,
Abstract summary: Diligent Learner framework suggests LLMs can achieve superintelligence via test-time search.<n>We design a benchmark to measure $$ on logical out-of-distribution inference.<n>We find that successful reasoning at scale is contingent upon precise tool calls.
Score: 7.762021543059531
License: http://creativecommons.org/licenses/by/4.0/
Abstract: The Diligent Learner framework suggests LLMs can achieve superintelligence via test-time search, provided a sufficient step-success probability $γ$. In this work, we design a benchmark to measure $γ$ on logical out-of-distribution inference. We construct a class of tasks involving GF(2) circuit reconstruction that grow more difficult with each reasoning step, and that are, from an information-theoretic standpoint, impossible to reliably solve unless the LLM carefully integrates all of the information provided. Our analysis demonstrates that while the $γ$ value for small LLMs declines superlinearly as depth increases, frontier models exhibit partial robustness on this task. Furthermore, we find that successful reasoning at scale is contingent upon precise tool calls, identifying tool design as a critical capability for LLMs to achieve general superintelligence through the Diligent Learner framework.

Related papers

SELT: Self-Evaluation Tree Search for LLMs with Task Decomposition [5.5688696788198975]
We introduce SELT (Self-Evaluation LLM Tree Search), a novel framework to enhance LLM reasoning without relying on external reward models.<n>We validate our approach on challenging benchmarks, including the knowledge-based MMLU and the Tool Learning dataset Seal-Tools.
arXiv Detail & Related papers (2025-06-09T08:52:27Z)
Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers [74.17516978246152]
Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques.<n>We propose EXSEARCH, an agentic search framework, where the LLM learns to retrieve useful information as the reasoning unfolds.<n>Experiments on four knowledge-intensive benchmarks show that EXSEARCH substantially outperforms baselines.
arXiv Detail & Related papers (2025-05-26T15:27:55Z)
TUMS: Enhancing Tool-use Abilities of LLMs with Multi-structure Handlers [8.34574238496256]
We propose TUMS, a novel framework designed to enhance the tool-use capabilities of large language models.<n>Our framework consists of four key components: (1) an intent recognizer that identifies the user's intent to help LLMs better understand the task; (2) a task decomposer that breaks down complex tasks into simpler subtasks, each involving a tool call; and (3) a subtask processor equipped with multi-structure handlers to generate accurate parameters.<n>Our empirical studies have evidenced the effectiveness and efficiency of the TUMS framework with an average of 19.6% and 50.6% improvement separately on easy and hard
arXiv Detail & Related papers (2025-05-13T09:57:28Z)
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.<n>Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.<n>We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
arXiv Detail & Related papers (2025-02-04T17:26:58Z)
Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning. We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
arXiv Detail & Related papers (2024-06-20T13:08:09Z)
FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition [56.76951887823882]
Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks. We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
arXiv Detail & Related papers (2024-02-29T21:05:37Z)
Efficient Tool Use with Chain-of-Abstraction Reasoning [63.08202389132155]
Large language models (LLMs) need to ground their reasoning to real-world knowledge.<n>There remains challenges for fine-tuning LLM agents to invoke tools in multi-step reasoning problems.<n>We propose a new method for LLMs to better leverage tools in multi-step reasoning.
arXiv Detail & Related papers (2024-01-30T21:53:30Z)
From Good to Great: Improving Math Reasoning with Tool-Augmented Interleaf Prompting [45.77084082197953]
IMP-TIP: Improving Math Reasoning with Tool-augmented Interleaf Prompting. We introduce IMP-TIP: Improving Math Reasoning with Tool-augmented Interleaf Prompting.
arXiv Detail & Related papers (2023-12-18T06:31:23Z)
TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models [52.734140807634624]
Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. Existing continual learning benchmarks lack sufficient challenge for leading aligned LLMs. We introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
arXiv Detail & Related papers (2023-10-10T16:38:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.