A glovebox robotic lab with agentic LLM reasoning synthesized 352 lithium halide spinel samples, covering 72% of possible metal combinations and raising the rate of good ionic conductors from 1.33% to 5.33% over the campaign.
hub Canonical reference
CAS- CADE: Cumulative agentic skill creation through autonomous development and evolution
Canonical reference. 100% of citing Pith papers cite this work as background.
17
Pith papers citing it
2
external citations · external index
Background
100% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
years
2026 17roles
background 4polarities
background 4representative citing papers
Framework estimates context-dependent marginal utility of candidate skills via reward gaps in matched base vs. skill-augmented rollouts to filter skills and co-train policy as generator.
False-pass bias in LLM judges disables contribution-based skill retirement past a sharp threshold, while symmetric noise does not, and the failure is often silent in aggregate metrics.
Skill coverage measures which natural-language skill constraints an LLM agent trajectory exercises and passes, revealing low coverage on SkillsBench and enabling a 16% recovery of failed tasks via targeted skill emphasis.
Decentralized AI agent teams self-organize around hypotheses, critique proposals, and share knowledge to outperform single-agent baselines on biomedical ML, language-model optimization, and protein fitness tasks.
A governance recipe—retire under-performing skills, cap the active set, and impose a meta-skill authoring style—raises held-out MBPP+ hard-100 pass@1 from 0.258 to 0.584, though the ungoverned 'drift' baseline itself is never run.
SearchSkill improves LLM query planning on knowledge QA by using explicit skill selection from an evolving SkillBank and a two-stage SFT process that aligns training with inference-time skill-grounded execution.
DRIVE disentangles reasoning and interaction skills for web agents via dual-level modeling and scene-aware coordination, reaching 52.8% success on WebArena tasks.
The paper introduces the KDR task, HKA multi-agent framework, and KDR-Bench to enable LLM agents to integrate structured knowledge into deep research reports, with experiments showing outperformance over prior agents.
Memory, skills, and rules in LLM agents sit on one compression spectrum, and no system yet supports adaptive cross-level compression.
Agon is a new autonomous research system using prompt economy loops across 444 iterations to demonstrate scalable omnidisciplinary research and a taxonomy separating machine-fixable failures from those needing human judgment.
OpenSkill bootstraps LLM agent self-evolution by pulling grounded knowledge and anchors from open-world sources, synthesizing transferable skills, and refining them on self-generated virtual tasks, achieving top benchmark pass rates without supervision.
AtomisticSkills is a new harness framework with 100+ human-curated skills that lets general AI agents perform atomistic research tasks including simulations, screening, and analysis, shown on electrolyte design, CO2 capture, drug screening, and catalyst tasks.
SkillsVote is a governance system for agent skills that profiles corpora, recommends via search, and gates updates on successful reusable outcomes, yielding benchmark gains without model changes.
Paimon is an agentic framework that automates atomistic simulations and improves reliability by suppressing silent errors in agent workflows, demonstrated on liquid electrolyte cases and literature reproduction.
A survey that defines agent skills as reusable procedural artifacts and reviews methods, resources, and applications across their representation, acquisition, retrieval, and evolution stages.
citing papers explorer
-
Agentic LLM Reasoning in a Self-Driving Laboratory for Air-Sensitive Lithium Halide Spinel Conductors
A glovebox robotic lab with agentic LLM reasoning synthesized 352 lithium halide spinel samples, covering 72% of possible metal combinations and raising the rate of good ionic conductors from 1.33% to 5.33% over the campaign.
-
Co-Evolving Skill Generation and Policy Optimization
Framework estimates context-dependent marginal utility of candidate skills via reward gaps in matched base vs. skill-augmented rollouts to filter skills and co-train policy as generator.
-
The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
False-pass bias in LLM judges disables contribution-based skill retirement past a sharp threshold, while symmetric noise does not, and the failure is often silent in aggregate metrics.
-
Skill Coverage: A Test Adequacy Metric for Agent Skills
Skill coverage measures which natural-language skill constraints an LLM agent trajectory exercises and passes, revealing low coverage on SkillsBench and enabling a 16% recovery of failed tasks via targeted skill emphasis.
-
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Decentralized AI agent teams self-organize around hypotheses, critique proposals, and share knowledge to outperform single-agent baselines on biomedical ML, language-model optimization, and protein fitness tasks.
-
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries
A governance recipe—retire under-performing skills, cap the active set, and impose a meta-skill authoring style—raises held-out MBPP+ hard-100 pass@1 from 0.258 to 0.584, though the ungoverned 'drift' baseline itself is never run.
-
SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks
SearchSkill improves LLM query planning on knowledge QA by using explicit skill selection from an evolving SkillBank and a two-stage SFT process that aligns training with inference-time skill-grounded execution.
-
DRIVE: Modeling Skills at the Reasoning and Interaction Levels for Web Agents under Continual Learning
DRIVE disentangles reasoning and interaction skills for web agents via dual-level modeling and scene-aware coordination, reaching 52.8% success on WebArena tasks.
-
Towards Knowledgeable Deep Research: Framework and Benchmark
The paper introduces the KDR task, HKA multi-agent framework, and KDR-Bench to enable LLM agents to integrate structured knowledge into deep research reports, with experiments showing outperformance over prior agents.
-
Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents
Memory, skills, and rules in LLM agents sit on one compression spectrum, and no system yet supports adaptive cross-level compression.
-
Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy
Agon is a new autonomous research system using prompt economy loops across 444 iterations to demonstrate scalable omnidisciplinary research and a taxonomy separating machine-fixable failures from those needing human judgment.
-
OpenSkill: Open-World Self-Evolution for LLM Agents
OpenSkill bootstraps LLM agent self-evolution by pulling grounded knowledge and anchors from open-world sources, synthesizing transferable skills, and refining them on self-generated virtual tasks, achieving top benchmark pass rates without supervision.
-
Harnessing AtomisticSkills for Agentic Atomistic Research
AtomisticSkills is a new harness framework with 100+ human-curated skills that lets general AI agents perform atomistic research tasks including simulations, screening, and analysis, shown on electrolyte design, CO2 capture, drug screening, and catalyst tasks.
-
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
SkillsVote is a governance system for agent skills that profiles corpora, recommends via search, and gates updates on successful reusable outcomes, yielding benchmark gains without model changes.
-
A Robust Agentic Framework for Expert-Level Automation of Atomistic Simulations
Paimon is an agentic framework that automates atomistic simulations and improves reliability by suppressing silent errors in agent workflows, demonstrated on liquid electrolyte cases and literature reproduction.
-
A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications
A survey that defines agent skills as reusable procedural artifacts and reviews methods, resources, and applications across their representation, acquisition, retrieval, and evolution stages.
- Ratchet: How Reliable Must an LLM Judge Be to Retire a Skill?