REVIEW 14 cited by
Large Language Models as Tool Makers
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent research has highlighted the potential of large language models (LLMs) to improve their problem-solving capabilities with the aid of suitable external tools. In our work, we further advance this concept by introducing a closed-loop framework, referred to as LLMs A s Tool Makers (LATM), where LLMs create their own reusable tools for problem-solving. Our approach consists of two phases: 1) tool making: an LLM acts as the tool maker that crafts tools for a set of tasks. 2) tool using: another LLM acts as the tool user, which applies the tool built by the tool maker for problem-solving. On the problem-solving server side, tool-making enables continual tool generation and caching as new requests emerge. This framework enables subsequent requests to access cached tools via their corresponding APIs, enhancing the efficiency of task resolution. Recognizing that tool-making requires more sophisticated capabilities, we assign this task to a powerful, albeit resource-intensive, model. Conversely, the simpler tool-using phase is delegated to a lightweight model. This strategic division of labor allows the once-off cost of tool-making to be spread over multiple instances of tool-using, significantly reducing average costs while maintaining strong performance. Furthermore, our method offers a functional cache through the caching and reuse of tools, which stores the functionality of a class of requests instead of the natural language responses from LLMs, thus extending the applicability of the conventional cache mechanism. We evaluate our approach across various complex reasoning tasks, including Big-Bench tasks. With GPT-4 as the tool maker and GPT-3.5 as the tool user, LATM demonstrates performance equivalent to using GPT-4 for both roles, but with a significantly reduced inference cost.
Forward citations
Cited by 14 Pith papers
-
Beyond Task Completion: A Verification-vs.-Conformance Gap in Tool-Evolving Agents
Synthesized tools from tool-evolving agents pass in-session checks but 96.8% of 222 tools score C=0.00 on held-out conformance suites that hand-written references pass perfectly.
-
HSS-Synth: Humanities and Social Sciences Data Synthesis for LLMs
HSS-Synth generates 230k instruction-tuning samples for 14 humanities/social-science fields and reports state-of-the-art fine-tuning results on 16 benchmarks.
-
Agentic Re-Casting using Agentic Re-Simulations
An agentic AI system with a physicist in the loop re-casts an ATLAS ttZ measurement into a global top-quark SMEFT fit and recovers injected coloron Wilson coefficients in a repeatable benchmark.
-
PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents
A multi-agent repair framework that samples multiple edit locations and iteratively reflects on patch attempts reaches 76.0% Pass@1 on SWE-bench-Verified, up to a 7.8% relative gain over SWE-agent.
-
Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries
Dynamic agent skill libraries are lifecycle-managed evolving stores whose admission, verification, maintenance, and retrieval choices determine whether reuse helps or hurts.
-
UltraCUA: A Foundation Model for Computer Use Agents with Hybrid Action
Training computer-use agents on a hybrid GUI-plus-programmatic-tool action space, with SFT and online RL, improves OSWorld success by ~23% relative over GUI-only baselines and transfers to Windows without Windows-spec...
-
RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving
RepoMaster, a repository-aware code agent, lifts the task pass rate from 40.7% to 62.9% and cuts token use by about 95% versus OpenHands on the new GitTaskBench benchmark.
-
Safety Degradation in AI Agents
Adding retrieval to aligned LLMs degrades safety: refusal rates fall, bias and harmfulness rise, and prompt-based mitigation only partially restores alignment.
-
FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
FlowEvo compiles successful agent workflows into executable skill records and reuses them at inference time, reporting the best accuracy-cost tradeoff across ALFWorld, HumanEval, and GSM8K among tested baselines.
-
AutoTool: Dynamic Tool Selection and Integration for Agentic Reasoning
AutoTool's two-phase SFT/RL plus ranking training lets 8B LLM agents beat larger fixed-tool agents across math, search, code, and vision benchmarks, though unseen-tool gains are asserted, not isolated.
-
A Compute-Matched Re-Evaluation of TroVE on MATH
After matching computational budget, TroVE's toolbox mechanism yields only a marginal, statistically non-significant 1% accuracy gain over a plain sampling baseline on MATH.
-
Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration
MAEL gives each agent in a multi-agent LLM system an experience pool and retrieves high-reward past steps to guide new task solving.
-
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
Reinforcing the two experts most correlated with thinking tokens improves reasoning accuracy and efficiency in MoE large reasoning models, with gains of up to 10 points on AIME benchmarks.
-
Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
The paper surveys agent skills for LLMs across architecture, acquisition, deployment, and security, proposing a four-tier Skill Trust and Lifecycle Governance Framework to address vulnerabilities in community skills.
Discussion (0). Sign in to comment.