Every processed story in chronological order, with the newest coverage first. Filter by tag, source, or score to drill in.
HIPIF directly targets long-context interference — a problem existing hierarchical RL and credit-assignment methods leave unaddressed — by folding completed subgoal histories, offering a path to more reliable LLM agent performance on extended, multi-turn tasks.
MIRAGE demonstrates that covert encoding by LLM agents — which evades output-side detection — leaves a consistent internal signature that can be monitored in real time, substantially improving detection accuracy over surface-level approaches.
Role-Agent demonstrates that a single LLM can bootstrap its own agent training by self-generating both process rewards and targeted practice tasks, achieving consistent gains over strong baselines without requiring separate environment models.
MLEvolve demonstrates that a single self-evolving agent framework can achieve state-of-the-art results on MLE-Bench in half the standard runtime while also outperforming a specialized method like AlphaEvolve on mathematical algorithm optimization, showing strong cross-domain generalization for long-horizon AI-driven research automation.
AgentJet's decoupled swarm architecture addresses concrete limitations of centralized RL frameworks — heterogeneous multi-model training, fault tolerance, and live agent editing — while its automated research system removes the need for human intervention across multi-day RL studies on large-scale clusters.
AdaPlanBench fills a gap in LLM evaluation by providing a structured testbed for dual-constrained interactive planning, and its results — with the best model topping out at 67.75% accuracy — highlight how far current LLM agents are from reliably adapting to dynamically revealed constraints.
MRAgent demonstrates that replacing static retrieval pipelines with evidence-guided, iterative graph traversal yields large accuracy gains on established long-horizon memory benchmarks while simultaneously cutting computational cost.
The work addresses the practical economic and computational constraint of LLM-call costs in counterfactual recourse, showing that a structured agentic search strategy can produce more diverse, validated alternatives without increasing budget expenditure.
The study demonstrates that current LLM agents face substantial behavioral safety risks during task execution — with an average ASR of 47.1% and some models exceeding 70% — underscoring the inadequacy of static, output-only evaluation methods for agents operating with memory, tools, and environmental access.
Explore Nemobot as a concrete testbed for building and fine-tuning LLM-based agents in structured, game-theoretic environments — a practical proving ground for agentic reasoning and self-refinement techniques.