…Further analysis shows that additional agent steps do not necessarily improve performance, suggesting that the key bottleneck is maintaining a correct analytical state rather than increasing interaction budget . We release LongDS to…
…Yet existing benchmark s for frontier models primarily evaluate either single-turn responses or short-horizon agent trajectories, failing to capture the challenges of sustained iterative improvement over extended time horizons. To…
…We evaluate native LLMs, Hybrid RAG , and three research-agent adaptations across four backbones. Results show that explicit evidence organization improves traceability and factual support, but gains depend strongly on the decision…
…Self-Evaluated Process Rewards for Retrieval-Augmented Agents (2026) Improving Search Agent with One Line of Code (2026) Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization (2026) PRAISE…
…Observability-Driven Automatic Evolution of Coding-Agent Harnesses (2026) Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use (2026) Continual Harness: Online Adaptation for Self-Improving Foundation Agents (2026) RoboPhD…
…Learning Self-Evolving Skills for Coding Agents (2026) SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision (2026) Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills (2026…
…Across five GUI-grounding benchmarks and multiple Qwen backbones, VISTA consistently improves accuracy. On ScreenSpot-Pro, it improves Qwen3-VL 4B/8B/30B-A3B from 55.5/52.7/53.7 to…
…Agents Published on May 7 Submitted by taesiri on May 8 Authors: , , , , , , , , , , , , , , , Abstract SkillOS enables self-evolving LLM agents to learn complex long-term skill curation policies through reinforcement learning, improving performance…
…that dynamically evolves memory topology through three stages to improve performance in complex agentic environments. AI-generated summary Existing memory-augmented LLM agents often treat memory as a static repository with pre…
…optimization , and replay/recomposition for self-improvement. We ground the framework with case studies in math, code/SQL, multimodal reasoning, tool-using agents, and agentic skill benchmarks that evaluate skill induction, reuse…