Kari Jaaskelainen

InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios

Auto-constructing, auditing, routing, and evolving multi-agent DAGs—at enterprise scale. Building capable LLM agents typically demands bespoke workflows, brittle prompts, and expert iteration. InfiAgent proposes a general, self-evolving alternative: a pyramid-like, DAG-based multi-agent framework that decomposes complex work into hierarchical, reusable “agent-as-a-tool” components—then continually restructures itself as tasks change.

By Kari Jaaskelainen

REMA: A Unified Reasoning Manifold Framework for Interpreting Large Language Model

Diagnosing LLM reasoning failures as geometric deviations from a low-dimensional manifold. Why do large language models succeed—or fail—on complex reasoning? REMA reframes the question geometrically. It posits a Reasoning Manifold: a low-dimensional structure formed by internal representations associated with correct reasoning trajectories. Errors, then, are measurable deviations from

By Kari Jaaskelainen

Retrieval-Augmented Guardrails for AI-Drafted Patient-Portal Messages: Error Taxonomy Construction and Large-Scale Evaluation

Clinician-grade guardrails: retrieval-augmented, clinically grounded, and validated on real patient messages. As patient-portal messaging grows, so does the pressure on clinicians—and the appeal of LLM-drafted replies. But drafts can miss context, introduce clinical inaccuracies, or adopt the wrong tone. This work delivers a practical solution: a retrieval-augmented evaluation pipeline

By Kari Jaaskelainen

See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation

Turning natural-language intent into flight paths with waypoint grounding—no training required. See, Point, Fly (SPF) reimagines vision-and-language navigation for drones by treating action selection as spatial grounding—not text generation. Instead of “talking” a UAV through step-by-step actions, SPF asks a vision-language model (VLM) to iteratively mark 2D waypoints

By Kari Jaaskelainen
See all