Challenge: LLM-based agents are powerful tools for automating complex scientific workflows, especially in chemistry, but their single-task performance is limited by tool constraints.
Approach: They propose a framework that optimizes the collective capabilities of specialized tools by dynamic coordination within individual tasks.
Outcome: The proposed framework outperforms chemistry-specialized models, generalist LLMs, and agent systems with tool orchestration.

Similar Papers

Tooling or Not Tooling? The Impact of Tools on Language Agents for Chemistry Problem Solving (2025.findings-naacl)

Copied to clipboard

Challenge: Existing evaluations of large language models (LLMs) with tools are limited and qualitative . existing evaluations have been limited and only focus on 14 tasks focusing on compound synthesis.
Approach: They propose to develop an enhanced chemistry agent over ChemCrow to improve chemistry problem solving by integrating tools into LLMs.
Outcome: The proposed agent does not consistently outperform its base LLMs without tools on specialized chemistry tasks and general chemistry questions.
MT-Mol: Multi Agent System with Tool-based Reasoning for Molecular Optimization (2025.findings-emnlp)

Copied to clipboard

Challenge: Structured reasoning and tool-grounded molecular optimization are still underexplored.
Approach: They propose a framework for molecular optimization that leverages tool-guided reasoning and role-specialized LLM agents.
Outcome: a new framework outperforms existing LLM frameworks on 15 of 23 tasks.
ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for extracting chemical procedures from literature are insufficient and low-quality due to the inherent ambiguity of chemical language and the high cost of human annotation.
Approach: They propose a fully fine-tuned large language model (LLM) as a chemical executor to convert between unstructured experimental procedures and structured action sequences.
Outcome: The proposed model outperforms the baseline model on R2D and D2A tasks by 10%.
Learning to Use Tools via Cooperative and Interactive Agents (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for large language models (LLMs) use one agent to iterate and execute tools, but they suffer from performance degradation when addressing practical tasks.
Approach: They propose a tool learning framework that coordinates three specialized agents for tool selection, tool execution, and action calibration separately.
Outcome: The proposed framework outperforms baseline models on three datasets with 14% higher success rate.
CAR: Empowering Agents with Dynamic Tool Synthesis and Global Trajectory Rectification (2026.findings-acl)

Copied to clipboard

Challenge: Existing LLM agents are brittle in open-ended environments due to two limitations: 1) a closed action space; 2) myopic error recovery.
Approach: They propose a novel architecture that augments the action space and revises global strategies by adding a reflective replanning mechanism to the system.
Outcome: Experiments show that CAR outperforms baselines in a diagnostic benchmark with pruned toolsets to simulate tool scarcity.
ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering (2026.acl-long)

Copied to clipboard

Challenge: Large language model (LLM) agents often face strict input context limits, preventing efficient consideration of large toolsets.
Approach: They propose a tool that allows LLMs to merge tools with auto-correction and toolScopeRetriever to rank and select only the most relevant tools for each query.
Outcome: Evaluations on three state-of-the-art LLMs and three open-source tool-use benchmarks show gains of 8.38% to 38.6% in tool selection accuracy.
Evaluating Multi-Hop Reasoning in Large Language Models: A Chemistry-Centric Benchmark (2026.findings-eacl)

Copied to clipboard

Challenge: a new pipeline for compositional multi-hop reasoning in large language models is being developed . a recent study shows that even state-of-the-art models struggle with compositional reasoning .
Approach: They propose a pipeline that builds benchmarks from proprietary or public data . they use generative reasoning models, chemical named-entity recognition, and external knowledge bases to build knowledge graphs.
Outcome: The proposed pipeline compares state-of-the-art models with and without retrieval augmentation . the pipeline is generalizable with fine-tuning, enabling creation of challenging benchmarks .
Towards Unified Task Embeddings Across Multiple Models: Bridging the Gap for Prompt-Based Large Language Models and Beyond (2024.findings-acl)

Copied to clipboard

Challenge: Existing task embedding methods rely on fine-tuned, task-specific language models, which hinders their adaptability to prompt-guided Large Language Models (LLMs).
Approach: They propose a framework for unified task embedding that harmonizes task embeds from various models within a single vector space.
Outcome: The proposed framework harmonizes task embeddings from various models within a single vector space.
Small LLMs Are Weak Tool Learners: A Multi-LLM Agent (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have revolutionized natural language processing with impressive capabilities, but they lack domain specificity, real-time information and face challenges in solving specialized problems.
Approach: They propose a multi-LLM approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer.
Outcome: The proposed model outperforms existing models by demonstrating its effectiveness and advantages in tool learning.
CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluations of Large Language Models (LLMs) focus on task completion, but neglect a crucial capability: the ability to devise and adjust cost-optimal plans in response to changing environments.
Approach: They propose a scalable, cost-centric benchmark to evaluate agents’ economic reasoning and replanning abilities.
Outcome: Evaluating leading open-sourced and proprietary models on CostBench reveals a substantial gap in cost-aware planning .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations