SkillWeaver introduces a decompose-retrieve-compose framework for LLM agents, formalizing the Compositional Skill Routing problem. It achieves 67.7% decomposition accuracy via Iterative Skill-Aware Decomposition (SAD), improving from 51.0% with a p-value of less than 10^-6, and reduces context window usage by over 99%.
arxiv
arXiv cs.CL
·
76d ago
·
research
SkillWeaver: Compositional Skill Routing for LLM Agents
from English
Importance 3/3
New feature vs. leaders
New harness with differentiators
arXiv cs.CL
OpenAI
Cohere
Mistral AI
AI agents
Reasoning models
Training methods
Related articles
arxiv
arXiv cs.AI
·
75d ago
·
4 views
Trajectory Mining Reveals Skill Structure but Fails to Improve Policies
A three-stage pipeline mines skill libraries from GUI interaction data, achieving high purity in five of eight clusters against InteraSkill labels. However, the method only slightly improves skill-step accuracy on IW and fails to advance performance on BrowseComp+ or key metrics, indicating limitations in cross-domain policy transfer.
arxiv
arXiv cs.CL
·
76d ago
·
3 views
LegalHalluLens: Auditing Hallucinations in Legal AI
LegalHalluLens introduces a framework to audit AI hallucinations in legal contexts by analyzing typed hallucination profiles across four claim categories. It reveals a 38-40 point gap between obligation/numeric and temporal claims, and shows two systems with identical 52% hallucination rates can have opposite risk directions. The framework uses a Risk Direction Index and calibrated debate pipelines to reduce fabricated detections by 45% and improve accountability in legal AI deployment.
arxiv
arXiv cs.CL
·
78d ago
·
3 views
DeepRubric: Efficient RL for Deep Research Agents
DeepRubric introduces a data construction framework that builds query-rubric pairs by first defining verifiable evaluation targets through an evidence tree. It generates 9K supervision examples and trains a 8B model with GRPO, achieving performance comparable to state-of-the-art models using 13x fewer RL GPU-hours.
arxiv
arXiv cs.LG
·
78d ago
·
4 views
Fingerprinting agent behavior through procedural trajectories
We introduce a method to identify agents by their procedural behavior fingerprints, achieving 85.7% accuracy in attributing unseen trajectories to correct agents. Using ProcGrep, we analyze coding agent behavior in SWE-Bench, finding that models from similar release periods or distilled from each other exhibit closer behavioral similarity, with a Jensen-Shannon divergence of 0.25.
arxiv
arXiv cs.AI
·
74d ago
·
4 views
LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents
LedgerAgent introduces a structured ledger to maintain task states separately in tool-calling agents. It renders states into prompts and enforces policy constraints before tool execution, reducing policy violations and improving performance across customer-service domains.