Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

TOPIC · ENTITY #461

web agents

Related event timeline, sources and context from the news index.

EVENT TIMELINE

3

RESEARCH · 1 SOURCE · arXiv cs.AI

SkillShift-Bench: benchmark for skill learning under open-environment shifts

SkillShift-Bench is a new benchmark and suite of three self-hosted web environments (with code and a leaderboard) that evaluates skill learning for web agents under controlled Contextual, Perceptual, and Execution shifts. Experiments show systematic robustness degradation — lower success, higher interaction cost, and more skill failures (Execution Shift hardest) — and the paper frames shifted skill execution as a nonstationary local executability problem, offering a dynamic-regret analysis and a test-time adaptation method to improve execution without relearning skills.

7.0

RESEARCH · 1 SOURCE · arXiv cs.AI

EconSkills: skill library and evaluation for web agents retrieving live economic data (arXiv:2609.19523v1)

The paper introduces EconSkills, a skill library and evaluation framework that converts verified EconWebArena browser trajectories into parameterized standard operating procedures for retrieving live economic data. Experiments show that abstracted skills improve transfer in controlled settings versus no-skill prompting, that library-scale retrieval is competitive but best on directly covered tasks, and that coverage-aware selection and semantic verification remain important.

6.0

RESEARCH · 1 SOURCE · arXiv cs.AI

OdoBot: Token-efficient web-agent architecture via application behavior modeling

An arXiv preprint introduces OdoBot, a web-agent architecture that builds a behavioral model of a web application from successful task-execution demonstrations to reduce token usage. In experiments on 45 tasks in the Canvas LMS, OdoBot used 44% and 80% fewer tokens than Agent-E and WebVoyager respectively, and it outperformed WebVoyager on task success rate.

6.0