Pith. sign in

REVIEW 13 cited by

SciAgent: Tool-augmented Language Models for Scientific Reasoning

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

arxiv 2402.11451 v2 pith:V4AUPFAZ submitted 2024-02-18 cs.CL cs.AI

classification cs.CLcs.AI
keywords llmsscientificreasoningsciagentsettingtool-augmentedlanguagemathfunc
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Scientific reasoning poses an excessive challenge for even the most advanced Large Language Models (LLMs). To make this task more practical and solvable for LLMs, we introduce a new task setting named tool-augmented scientific reasoning. This setting supplements LLMs with scalable toolsets, and shifts the focus from pursuing an omniscient problem solver to a proficient tool-user. To facilitate the research of such setting, we construct a tool-augmented training corpus named MathFunc which encompasses over 30,000 samples and roughly 6,000 tools. Building on MathFunc, we develop SciAgent to retrieve, understand and, if necessary, use tools for scientific problem solving. Additionally, we craft a benchmark, SciToolBench, spanning five scientific domains to evaluate LLMs' abilities with tool assistance. Extensive experiments on SciToolBench confirm the effectiveness of SciAgent. Notably, SciAgent-Mistral-7B surpasses other LLMs with the same size by more than 13% in absolute accuracy. Furthermore, SciAgent-DeepMath-7B shows much superior performance than ChatGPT.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Investigating the (De)Composition Capabilities of Large Language Models in Natural-to-Formal Language Conversion

    cs.CL 2025-01 conditional novelty 7.0 of 10

    LLMs show measurable deficiencies in both decomposition and composition during natural-to-formal conversion, with decomposition errors dominating, under the new DEDC evaluation framework.

  2. RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts

    cs.LG 2024-11 conditional novelty 7.0 of 10

    AI agents beat human ML experts on short (2-hour) research-engineering tasks, but human experts outperform agents given 8+ hour budgets, measured on seven new open-source RE-Bench environments.

  3. NNStar: An end-to-end AI agent for nuclear matter and neutron star physics

    nucl-th 2026-07 conditional novelty 6.0 of 10

    NNStar packages the RMF-to-neutron-star pipeline as a portable LLM-agent skill, validated on TM1/NL3/FSU-δ6.7 and demonstrated by an autonomous σ6-extended TM1 fit.

  4. SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents

    cs.CL 2026-02 conditional novelty 6.0 of 10

    SciAgent-8B, fine-tuned on trajectories synthesized from a tool dependency graph, outperforms Qwen3-VL-235B-Instruct on SciAgentBench, a new 259-task benchmark for multi-step scientific tool-use.

  5. UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models

    cs.CL 2025-02 conditional novelty 6.0 of 10

    UGPhysics is a new bilingual benchmark of 5,520 undergraduate physics problems; the strongest tested LLM, OpenAI o1-mini, reaches only 49.8% accuracy.

  6. Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines

    cs.AI 2024-12 conditional novelty 6.0 of 10

    A multi-agent LLM framework builds AI model pipelines from ambiguous natural-language queries, improving exact-match accuracy from 15.7% to 25.2% on a 441-example benchmark.

  7. Learning to Solve Domain-Specific Calculation Problems with Knowledge-Intensive Programs Generator

    cs.CL 2024-12 conditional novelty 6.0 of 10

    A pipeline that generates executable programs from domain knowledge documents and uses them with extracted variables to solve domain-specific calculation problems, improving accuracy over baselines in legal and medical QA.

  8. An Auditable Agent Platform For Automated Molecular Optimisation

    cs.LG 2025-08 conditional novelty 5.0 of 10

    A hierarchical multi-agent LLM platform with recorded provenance improved average predicted binding affinity for AKT1 by 31%, while single-agent runs favored drug-likeness.

  9. CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning

    cs.LG 2025-06 conditional novelty 5.0 of 10

    CheMatAgent uses hierarchical Monte Carlo tree search with separate policy and execution models, plus trained reward models, to improve tool selection and parameter filling on a new chemistry benchmark, ChemToolBench.

  10. Improving Physics Reasoning in Large Language Models Using Mixture of Refinement Agents

    cs.AI 2024-12 conditional novelty 5.0 of 10

    MoRA uses GPT-4o to detect miscomprehension, wrong-concept, and computational errors in open-source LLM solutions, then routes specialized agents to fix them, improving multiple-choice physics accuracy by up to 16 per...

  11. Toward Efficient Agents: Memory, Tool learning, and Planning

    cs.AI 2026-01 conditional novelty 3.0 of 10

    A survey that organizes efficiency techniques for LLM agents into memory, tool learning, and planning, and consolidates benchmarks and metrics for measuring cost-performance trade-offs.

  12. Reflections from the 2024 Large Language Model (LLM) Hackathon for Applications in Materials Science and Chemistry

    cs.LG 2024-11 unverdicted novelty 3.0 of 10

    A community report describing 34 hackathon-built LLM applications for materials science and chemistry, with reflections on the event format and preliminary project results.

  13. Scientific Hypothesis Generation and Validation: Methods, Datasets, and Future Directions

    cs.CL 2025-05 reject novelty 2.0 of 10

    A survey of LLM-based hypothesis generation and validation whose taxonomy is useful in outline but whose citations and tool descriptions are unreliable.

Pith tools