FlowAgent models tool chaining as continuous latent trajectory generation with conditional flow matching to deliver global planning, formal utility bounds, and better robustness on long-horizon tasks, plus a new plan-level benchmark.
hub
From llm reasoning to autonomous ai agents: A comprehensive review.arXiv preprint arXiv:2504.19678
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
hub tools
representative citing papers
Backward token warping in ViT-based MLLMs enables reliable reasoning from nearby viewpoints by preserving semantic coherence better than pixel-wise warping or fine-tuning baselines.
Assistive agents for BVI users need accessibility alignment as a core design goal, with a proposed lifecycle pipeline, because sighted assumptions cause unfixable failures in verification, risk, and interaction.
A learned orchestration policy for LLM agents that jointly optimizes task decomposition and selective routing to (model, primitive) pairs, delivering 77% macro pass@1 at 10x lower cost than strong baselines across 13 benchmarks.
LATTICE is a scalable LLM-judge benchmark for crypto agent decision support that reveals performance trade-offs among real-world copilots across dimensions and tasks.
QuantClaw dynamically routes precision in agent workflows to cut cost by up to 21.4% and latency by 15.7% while keeping or improving task performance.
A small set of sparse autoencoder features in LLMs drives shifts between generous and selfish allocations in dictator games, with causal patching and steering confirming their role and generalization to other social games.
EvoOR-Agent co-evolves agent architectures as AOE-style networks with graph-mediated recombination and knowledge-base-assisted mutation to outperform fixed LLM pipelines on OR benchmarks.
MemSearch-o1 mitigates memory dilution in agentic LLM search through reasoning-aligned token-level memory growth, retracing with a contribution function, and path reorganization, improving reasoning activation on benchmarks.
An empirical evaluation of 22 agentic frameworks on BBH, GSM8K, and ARC benchmarks shows stable performance in 12 frameworks but highlights orchestration failures and weaker mathematical reasoning.
AgentComm achieves nearly 50% bandwidth reduction in embodied agent communication via LLM semantic processing, importance-aware transmission, and a task knowledge base, with negligible impact on task completion.
STAR is a failure-aware Markovian router that learns recovery transitions from both successful and unsuccessful execution traces to improve multi-agent performance on spatiotemporal benchmarks.
Researchers developed a fast XGBoost-based detector using 42 runtime features to spot adversarial interaction patterns in LLM agents, running over 9 times faster than LLM detectors on synthetic multi-turn data.
AgentDID is a W3C-compliant decentralized identity system for AI agents enabling self-managed authentication and state verification via challenge-response.
An intention-aware semantic agent system for AI glasses reduces bandwidth by over 50% in simulations while preserving task performance through adaptive preprocessing guided by inferred user intentions.
A survey comparing classical multi-agent systems with large foundation model-enabled multi-agent systems, showing how the latter enables semantic-level collaboration and greater adaptability.
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.
Agentic RAG embeds agents with reflection, planning, tool use, and collaboration into retrieval pipelines to overcome static RAG limitations, and the survey offers a taxonomy by agent count, control, autonomy, and knowledge representation plus applications and open challenges.
This review synthesizes LLM uses in stock forecasting and catalogs key practical pitfalls from a hedge-fund viewpoint.
citing papers explorer
-
A Survey of Context Engineering for Large Language Models
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.