SENTINEL generates targeted tasks from model failures in a Controller-Proposer-Solver loop, raising Pass^1 from 66.4 to 74.9 on Tau2-Bench Retail and outperforming standard RL.
hub Canonical reference
ChemCrow: Augmenting large-language models with chemistry tools
Canonical reference. 85% of citing Pith papers cite this work as background.
45
Pith papers citing it
133
external citations · Pith
Background
85% of classified citations
abstract
Over the last decades, excellent computational chemistry tools have been developed. Integrating them into a single platform with enhanced accessibility could help reaching their full potential by overcoming steep learning curves. Recently, large-language models (LLMs) have shown strong performance in tasks across domains, but struggle with chemistry-related problems. Moreover, these models lack access to external knowledge sources, limiting their usefulness in scientific applications. In this study, we introduce ChemCrow, an LLM chemistry agent designed to accomplish tasks across organic synthesis, drug discovery, and materials design. By integrating 18 expert-designed tools, ChemCrow augments the LLM performance in chemistry, and new capabilities emerge. Our agent autonomously planned and executed the syntheses of an insect repellent, three organocatalysts, and guided the discovery of a novel chromophore. Our evaluation, including both LLM and expert assessments, demonstrates ChemCrow's effectiveness in automating a diverse set of chemical tasks. Surprisingly, we find that GPT-4 as an evaluator cannot distinguish between clearly wrong GPT-4 completions and Chemcrow's performance. Our work not only aids expert chemists and lowers barriers for non-experts, but also fosters scientific advancement by bridging the gap between experimental and computational chemistry.
hub tools
citation-role summary
background 11
method 2
citation-polarity summary
representative citing papers
SciTrace embeds cumulative safety deliberation and trajectory-aware verification into scientific agent pipelines, claiming SOTA safety gains and detection of 78.8% of compositional risks missed by single-step checks.
MolLingo introduces a multi-agent framework with BFE molecular representation and docking-grounded reasoning to outperform frontier LLMs on molecular design benchmarks including fourfold docking score gains.
LLM agents reach only 50.6% accuracy on chemical cost estimation within 25% error even with tools, dropping with noise due to parsing, pack selection, and tool-use failures.
AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction reducing lower-wall Cf RMSE by 7.89% on the periodic hill at Reh=5600 while using a vision-language gate to detect 14 of 16 silent failures missed by solver checks.
AstroAlertBench evaluates multimodal LLMs on astronomical classification accuracy, reasoning, and honesty using real ZTF alerts, revealing that high accuracy often diverges from self-assessed reasoning quality.
SkillFoundry mines heterogeneous scientific resources into a self-evolving library of validated agent skills, with 71.1% novelty versus prior libraries and measurable gains on coding benchmarks plus two genomics tasks.
LLMs perform adequately on bio-molecular classification tasks but remain weak on regression, with hybrid architectures outperforming others on long sequences and fine-tuning hurting generalization.
FORGE enforces security policies in agentic systems via Datalog over abstract predicates with an observability service and reference monitor that guarantees policy semantics when the environment contract holds.
A dimensionless capillary capture parameter C = max(Fx_γ + μ Fz_γ)/(μ Fp) predicts whether a drop captures or redeposits a particle across wettability and friction regimes.
MolSight injects molecular graph topology and image-derived SVG annotations into a vision-language model, reporting state-of-the-art results on image-to-SMILES, captioning, descriptor, and bioactivity tasks.
An empirical study evaluating tool-augmented LLM agents on 243 real-world energy analytics problems across data retrieval, knowledge interpretation, and quantitative modeling using domain-specific tools and multi-dimensional scoring.
Introduces BrainAgent, a hierarchical LLM multi-agent framework for automating brain signal workflows, plus a new evaluation benchmark.
SIGA is a coding-agent adapter using retrieval, procedural memory, and validation gates that raises success rate on GEOS from 0.720 to 0.789 while cutting variance 16x and matching expert quality in minutes instead of hours.
MLReplicate benchmark evaluates six autonomous systems on 45 manuscripts from ICML 2025 papers, finding that automated reviews accept flawed outputs with fabricated claims while human review exposes methodological failures, and that the cheapest system outperforms the most expensive by a wide margin
ToolMol integrates evolutionary algorithms with agentic LLMs and precise RDKit tools to optimize multi-objective drug properties, yielding ligands with over 10% better predicted binding affinity and 35% gains in absolute binding free energy on three protein targets.
ADKO is a decentralized framework where agents share compact GP-derived tokens and LM insights to achieve collaborative Bayesian optimization with a decomposed regret bound that includes compression and approximation losses.
FAME models scientific topic trajectories in continuous time to forecast paper impact more accurately than LLMs by aligning manuscripts with field momentum in a dynamic latent space.
YOTOnet achieves improved zero-shot cross-domain fault diagnosis on bearing datasets by combining a physics-aware invariant feature distiller with domain-conditioned sparse experts, showing performance scaling as more training domains are added.
A scoping review of 52 studies maps LLM-based pedagogical agents across education contexts and identifies four key design dimensions along with emerging trends.
Graphectory turns stochastic agent trajectories into analyzable graphs, showing that stronger models and successful fixes follow coherent localization-validation steps while failures are chaotic, and online detection plus rollback improves resolution rates by 6.9-23.5%.
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.
CFDLLMBench is a new benchmark suite with CFDQuery, CFDCodeBench, and FoamBench to evaluate LLMs on graduate-level CFD knowledge, numerical reasoning, and context-dependent code implementation.
IR-Agent is a multi-agent LLM framework that emulates expert IR spectral analysis procedures to improve molecular structure elucidation accuracy and adaptability.
citing papers explorer
-
SENTINEL: Failure-Driven Reinforcement Learning for Training Tool-Using Language Model Agents
SENTINEL generates targeted tasks from model failures in a Controller-Proposer-Solver loop, raising Pass^1 from 66.4 to 74.9 on Tau2-Bench Retail and outperforming standard RL.
-
SciTrace: Trajectory-Aware Safety Reasoning for Scientific Discovery Agents
SciTrace embeds cumulative safety deliberation and trajectory-aware verification into scientific agent pipelines, claiming SOTA safety gains and detection of 78.8% of compositional risks missed by single-step checks.
-
MolLingo: Molecule-Native Representations for LLM-Powered Scientific Agents
MolLingo introduces a multi-agent framework with BFE molecular representation and docking-grounded reasoning to outperform frontier LLMs on molecular design benchmarks including fourfold docking score gains.
-
Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning
LLM agents reach only 50.6% accuracy on chemical cost estimation within 25% error even with tools, dropping with noise due to parsing, pack selection, and tool-use failures.
-
AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents
AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction reducing lower-wall Cf RMSE by 7.89% on the periodic hill at Reh=5600 while using a vision-language gate to detect 14 of 16 silent failures missed by solver checks.
-
AstroAlertBench: Evaluating the Accuracy, Reasoning, and Honesty of Multimodal LLMs in Astronomical Classification
AstroAlertBench evaluates multimodal LLMs on astronomical classification accuracy, reasoning, and honesty using real ZTF alerts, revealing that high accuracy often diverges from self-assessed reasoning quality.
-
SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources
SkillFoundry mines heterogeneous scientific resources into a self-evolving library of validated agent skills, with 71.1% novelty versus prior libraries and measurable gains on coding benchmarks plus two genomics tasks.
-
The limits of bio-molecular modeling with large language models : a cross-scale evaluation
LLMs perform adequately on bio-molecular classification tasks but remain weak on regression, with hybrid architectures outperforming others on long sequences and fine-tuning hurting generalization.
-
Formal Policy Enforcement for Real-World Agentic Systems
FORGE enforces security policies in agentic systems via Datalog over abstract predicates with an observability service and reference monitor that guarantees policy semantics when the environment contract holds.
-
ChargeBD: Character-Aware Heterogeneous Agent Reasoning for Guided Engineering in Battery Development
A dimensionless capillary capture parameter C = max(Fx_γ + μ Fz_γ)/(μ Fp) predicts whether a drop captures or redeposits a particle across wettability and friction regimes.
-
MolSight: A Graph-Aware Vision-Language Model for Unified Chemical Image Understanding
MolSight injects molecular graph topology and image-derived SVG annotations into a vision-language model, reporting state-of-the-art results on image-to-SMILES, captioning, descriptor, and bioactivity tasks.
-
How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?
An empirical study evaluating tool-augmented LLM agents on 243 real-world energy analytics problems across data retrieval, knowledge interpretation, and quantitative modeling using domain-specific tools and multi-dimensional scoring.
-
BrainAgent: A Large Language Model-Driven Multi-Agent Framework for Autonomous Brain Signal Understanding
Introduces BrainAgent, a hierarchical LLM multi-agent framework for automating brain signal workflows, plus a new evaluation benchmark.
-
Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters
SIGA is a coding-agent adapter using retrieval, procedural memory, and validation gates that raises success rate on GEOS from 0.720 to 0.789 while cutting variance 16x and matching expert quality in minutes instead of hours.
-
MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility
MLReplicate benchmark evaluates six autonomous systems on 45 manuscripts from ICML 2025 papers, finding that automated reviews accept flawed outputs with fabricated claims while human review exposes methodological failures, and that the cheapest system outperforms the most expensive by a wide margin
-
ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery
ToolMol integrates evolutionary algorithms with agentic LLMs and precise RDKit tools to optimize multi-objective drug properties, yielding ligands with over 10% better predicted binding affinity and 35% gains in absolute binding free energy on three protein targets.
-
ADKO: Agentic Decentralized Knowledge Optimization
ADKO is a decentralized framework where agents share compact GP-derived tokens and LM insights to achieve collaborative Bayesian optimization with a decomposed regret bound that includes compression and approximation losses.
-
FAME: Forecasting Academic Impact via Continuous-Time Manifold Evolution
FAME models scientific topic trajectories in continuous time to forecast paper impact more accurately than LLMs by aligning manuscripts with field momentum in a dynamic latent space.
-
YOTOnet: Zero-Shot Cross-Domain Fault Diagnosis via Domain-Conditioned Mixture of Experts
YOTOnet achieves improved zero-shot cross-domain fault diagnosis on bearing datasets by combining a physics-aware invariant feature distiller with domain-conditioned sparse experts, showing performance scaling as more training domains are added.
-
A Scoping Review of Large Language Model-Based Pedagogical Agents
A scoping review of 52 studies maps LLM-based pedagogical agents across education contexts and identifies four key design dimensions along with emerging trends.
-
Process-Centric Analysis of Agentic Software Systems
Graphectory turns stochastic agent trajectories into analyzable graphs, showing that stronger models and successful fixes follow coherent localization-validation steps while failures are chaotic, and online detection plus rollback improves resolution rates by 6.9-23.5%.
-
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.
-
CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics
CFDLLMBench is a new benchmark suite with CFDQuery, CFDCodeBench, and FoamBench to evaluate LLMs on graduate-level CFD knowledge, numerical reasoning, and context-dependent code implementation.
-
IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared Spectra
IR-Agent is a multi-agent LLM framework that emulates expert IR spectral analysis procedures to improve molecular structure elucidation accuracy and adaptability.
-
GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
-
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
AgentHarm benchmark shows leading LLMs comply with malicious agent requests and simple jailbreaks enable coherent harmful multi-step execution while retaining capabilities.
-
A Survey on Large Language Model based Autonomous Agents
A survey of LLM-based autonomous agents that proposes a unified framework for their construction and reviews applications in social science, natural science, and engineering along with evaluation methods and future directions.
-
ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models
ReWOO decouples reasoning from tool observations in augmented language models, delivering 5x token efficiency and 4% higher accuracy on multi-step reasoning benchmarks like HotpotQA.
-
PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop Refinement
PAPERCLAW is a multi-agent system for end-to-end autonomous research paper generation from literature to output, with human refinement and LLM-judge evaluation showing strong results.
-
ARIA: A Causal-Aware Framework for Rescuing LLM Reasoning in Trustworthy Materials Discovery
ARIA is a three-tier causal framework that conditions LLM knowledge use on mechanistic completeness for forward prediction and inverse design of 2D materials, producing auditable traces.
-
Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators
Sibyl-AutoResearch introduces self-evolving trial-and-error harnesses with auditable conversion units that link trial signals to updated research behaviors and harness repairs in autonomous systems.
-
SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules
SciCore-Mol augments LLMs with three integrated modules for molecular perception, latent diffusion generation, and reaction reasoning, claiming an 8B open model competes with or exceeds proprietary systems on chemical tasks.
-
Code as Agent Harness
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
-
Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration
NEXUS is a code-centric multi-agent framework with hierarchical verification that autonomously constructs and refines neuroimaging workflows, outperforming static baselines on ADHD-200 and ADNI data.
-
The HTC-Claw: Automating Discovery through High-Throughput Computational Campaigns
HTC-Claw is a new intelligent high-throughput computing platform that decomposes research goals into adaptive task workflows for automated materials discovery.
-
Teaching Astronomy with Large Language Models
Structured integration of LLMs in astronomy education, including a domain-specific tutor and documentation requirements, leads to improved AI literacy and reduced student reliance on AI over the semester.
-
From Question Answering to Task Completion: A Survey on Agent System and Harness Design
Survey framing LLM agents as model-plus-harness systems, decomposing harness responsibilities, mapping them to tasks, and highlighting open challenges in evaluation, safety, and co-evolution.
-
AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery
A survey organizing AI-powered research automation into five workflow stages, defining AutoResearch and Vibe Research, and proposing five evaluation dimensions while noting domain-conditioned limits on autonomy.
-
EconAI: Dynamic Persona Evolution and Memory-Aware Agents in Evolving Economic Environments
EconAI adds memory weighting and economic sentiment indexing to LLM agents so they adapt short-term actions to long-term goals inside a single macro/micro simulation loop.
-
Bridging Perception and Action: A Lightweight Multimodal Meta-Planner Framework for Robust Earth Observation Agents
The LMMP framework improves tool-calling accuracy and task success rates for Earth observation agents by grounding plans in multimodal features and remote sensing expert knowledge via a two-stage training process.
-
Agentic Reasoning for Large Language Models
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
-
WisPaper: Your AI Scholar Search Engine
WisPaper integrates semantic search with agent-based validation, library organization, and personalized AI feeds into a closed-loop system that improves academic paper discovery and long-term awareness.
-
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
A survey that deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.
-
Materials Informatics Across the Length Scales
A survey of data-driven methods for materials modeling at nanoscale, mesoscale, and micro-to-continuum scales that identifies established capabilities, data quality issues, and obstacles to cross-scale integration.
- PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say