arxiv arXiv cs.AI · 52d ago · research

Skill-Guided Continuation Distillation for GUI Agents

from English

SGCD introduces an iterative framework to improve GUI agents by addressing supervision gaps in off-trajectory states. It extracts skills from both successful and failed rollouts, using them to guide policy continuations that are mixed with expert trajectories. On OSWorld-Verified, SGCD boosts success rates of three base models from low-30\% to over 50\%.

Importance 3/3 New feature vs. leaders New harness with differentiators arXiv cs.AI Mistral AI Google DeepMind OpenAI AI agents Evaluation & benchmarks Reasoning models

Read original

arxiv arXiv cs.CL · 51d ago · 2 views

AtomMem: Simple and Effective Memory System for LLM Agents

AtomMem introduces a memory system that stores high-value atomic facts from long-form interactions. It uses hierarchical event structures and temporal profiles to capture coherent episodic contexts and track evolving user attributes, enabling stable and efficient memory evolution. Experiments on the LoCoMo benchmark show AtomMem achieves state-of-the-art performance in reasoning tasks.

arxiv arXiv cs.CL · 51d ago

GEMS: Geometric Constraints Enable Multi-Semantic Superposition in LLMs

GEMS enables training-free superposition of multiple semantic directions in LLMs by addressing distributional deviation and directional interference through geometric constraints. On GSM8K, it maintains 98% accuracy with three non-mathematical directions, while unconstrained addition drops to 4%; on Wikitext-2, it increases PPL by only 2.2%.

arxiv arXiv cs.CL · 52d ago

EARS Framework Enhances Multi-Agent System Reliability

EARS introduces explanatory abstention in sub-agents to improve reliability in large-scale multi-agent systems. By providing actionable failure rationales to coordinators, EARS increases the overall response pass rate from 68.5% to 78.9% in a production e-commerce assistant.

arxiv arXiv cs.AI · 52d ago

AdsMind: Physics-Grounded Multi-Agent System for Adsorption Discovery

AdsMind is a closed-loop multi-agent system that uses machine learning force fields and feedback to correct errors in adsorption configuration searches on catalyst surfaces. It achieves 100% and 98.8% success rates on AA20 and OCD-GMAE62 benchmarks, reduces energy dispersion by 14-fold compared to baselines, and maintains correct adsorption-energy signs in DFT validation, outperforming open-loop LLM agents.

arxiv arXiv cs.LG · 53d ago

SkillMigrator: Transferable Interaction Patterns for Web Agent Efficiency

SkillMigrator learns reusable web skills by matching layout structures instead of element references. It stores each skill as a transferable interaction pattern with a structural sketch, enabling efficient skill transfer across sites. Compared to state-of-the-art methods, it reduces average LLM-action counts by 8-10% on WebArena and Mind2Web at matched success rates.