…We observed improvements in Agent's environment interaction KPI such as tool success rate and tool parameter accuracy . The framework also offers new metrics such as Execution Quality to generate new insights…
…And training becomes self-improving. 🚀 Cool paper - I liked the way "From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning" frames the problem without making it feel…
…Training Efficiency-Aware Web Agents via Adaptive Reward Gating Published on Jun 5 Submitted by dan on Jun 9 Authors: , , , , , , Abstract SlimSearcher is a framework that improves efficiency in deep research agents…
…On three agentic benchmarks under strict privacy settings, PAAC dominates the Pareto frontier of privacy and accuracy, improving average accuracy by 15-36\% and reducing average leakage by 2-6times over state…
…To close this gap, we propose SkeMex, a post-deployment self-evolution framework that improves medical agents through a skill-based memory without updating model weights. SkeMex distills informative interaction trajectories into…
…Amir Saeidi , , , , , , Abstract Failure-Aware Meta-Agentic framework improves open-source LLM performance in conversational scenarios by identifying common errors and deploying specialized agents to correct them. AI-generated summary Large Language…
…Yilun Zhao , , Tingyu Song , , , Abstract Researchers introduce BRIGHT-Pro, an expanded expert-annotated benchmark for reasoning-intensive retrieval, and RTriever-Synth, an aspect-decomposed synthetic corpus, to improve retriever performance through agentic…
…As model capabilities continue to improve, we argue that the bottleneck for autonomous scientific discovery is shifting from prescribing agent workflows to designing agent environments : the resources, constraints, and interfaces that shape…
…Zihao Li , , , , , , , , Jingrui He Abstract Eywa is a heterogeneous agentic framework that extends language-centric systems to scientific foundation models by integrating domain-specific models with language-based reasoning interfaces for improved…
…Horizon-agent Intrinsic Non-attack Trajectory Benchmark (2026) FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search (2026) Towards Self-Improving Error Diagnosis in Multi-Agent Systems (2026…
