← Back to all news

AI agents

Tool use, function calling, orchestration and the protocols that let models act rather than only answer.

15,750 stories · RSS feed

arXiv AI
Sep 10

Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models

Feyospace‑v1 describes a data‑centric framework that enables a seven‑person team to train open‑weight cyber agents, addressing bottlenecks such as environment cost, supervision, and teacher access. The system combines five complementary components—Choulea, SkyReal, Hongzwang, PSBreakup, and Kreator—to analyze reasoning, reduce sampling costs, bypass API limits, restore merged model capabilities, and convert expert interventions into trainable signals. Using a diverse data engine, the team produced 164,269 verified trajectories for supervised fine‑tuning, achieving an average 23.76% improvement on CyberGym and 10.49% on pooled CTF suites, with the final checkpoint ranking 10th on the CyberGym leaderboard and first among comparable‑scale models.

By Zongjie Li, Alan Z. W, John Nicolas J, Walter H. F, Scott Donald L, Gordon Y. P, Deke X Jr
agentsfine-tuningbenchmarks
More like this →
arXiv AI
Sep 10

Personalizing LLM Agent Memory Using Biometrics

The paper introduces Bio-Memory, a biometric-aware memory architecture for large language model agents that conditions memory retrieval on both semantic similarity and biometric matching. By augmenting each memory note with a biometric embedding, Bio-Memory filters retrieval candidates based on identity before ranking them semantically. Experiments on a 10-user shared-agent setting across face and palmprint benchmarks show significant improvements in distinguishing owner from non-owner queries, with up to a 27.29% F1 gain on CALFW and 25.75% on MS_Blue.

By Yanhong Qian, Qingguo Meng, Shihao Ding, Xingbo Dong, Zhe Jin, Hanrui Wang, Isao Echizen
llmsragagentsbenchmarks
More like this →
arXiv AI
Sep 10

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

The paper introduces Procedural Graphs, a framework that structures procedural knowledge for large language model agents as (procedure, relation, procedure) triplets, analogous to knowledge graphs for factual data. At each decision point, a guidance model uses the local subgraph to bias the agent’s next action, while an LLM refiner self‑evolves the graph by comparing failed and successful trajectories, editing its topology to improve performance. Experiments across various datasets, tasks, and LLMs show that Procedural Graphs consistently outperform memory‑based baselines, and the self‑evolution mechanism further enhances results without manual engineering.

By Yuxing Lu, Yicheng Chen, Shanchan Wu, Sercan \"{O}. Ar{\i}k
llmsagents
More like this →
arXiv AI
Sep 10

Tracking the Moving Frontier: Long-Short Term Advantage Estimator

The paper introduces Long-Short Term Advantage Estimator (LSTAE), a single‑stream reinforcement learning algorithm that replaces repeated within‑iteration trajectory sampling with historical experience for advantage estimation. LSTAE tracks each task anchor with a drift‑aware long‑term baseline and a short‑term state‑experience buffer, converting accumulated experience into multi‑granular credit signals while requiring only one rollout per anchor. Experiments on agentic and mathematical reasoning benchmarks show that LSTAE matches or surpasses strong group‑based baselines while significantly reducing rollout cost.

By Xinhao Yao, Lu Yu, Changhao Wang, Fengwei Teng, Yuyao Zhang, Qing Cui, Jun Zhou, Yong Liu
agentsreinforcement-learningbenchmarks
More like this →
arXiv AI
Sep 10

AgentLeak: Cloning Stronger LLM Agent Capabilities onto Weaker Agents Beyond Skill Stealing

The paper introduces AgentLeak, a black‑box attack that clones the task‑solving capabilities of a strong LLM agent onto a weaker one by exploiting differences between successful and failed executions. Unlike prior skill‑stealing methods that only recover explicit skill artifacts, AgentLeak identifies and incorporates missing procedural behaviors, boosting task pass rates by over 40% and closing more than 80% of the capability gap across 20 scenarios. The study demonstrates that observable execution behavior can leak proprietary procedural knowledge, posing a confidentiality risk for LLM agents.

By Xiaoting Lyu, Yuhong Wu, Yufei Han, Shichang Liu, Liang Zhang, Bin Wang, Bin Wang, Xiaobo Ma, Wei Wang
llmsagents
More like this →
arXiv AI
Sep 10

BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints

BlueprintAgent (BPA) is a multimodal agent that converts scanned reinforced‑concrete building blueprints into simulation‑ready frame models by treating a large language model (MLLM) as the primary reader and decision maker, while OCR and computer vision provide localized evidence. BPA implements engineering constraints as callable validators that trigger targeted MLLM revisits over specific regions, enabling precise beam‑column support, span count, and 3D continuity checks. In evaluations on 300 real scanned sheets from 20 projects, BPA achieved a macro‑averaged Beam F1 of 0.994, vastly outperforming single‑MLLM zero‑shot (0.301) and fixed‑pipeline (0.820) baselines.

By Zhouyuan Xu, Chen Yang, Linhao Wang, Jiansheng Fan, Chen Wang
llmsagentscomputer-visionmultimodalsafety
More like this →
arXiv AI
Sep 10

Riemannian Optimization for Multi-Player Quantum Games on Product Unitary Manifolds

The paper extends the Eisert-Wilkens-Lewenstein quantum game to multiplayer settings with mixed strategies, where each player selects unitary operators and mixes them classically. It introduces the Unitary Strategy Matrix Exponential Algorithm (USMEA), a geometry-aware sequential method that jointly learns local unitary actions and mixing probabilities for each player. The authors analyze USMEA’s convergence under standard conditions and confirm the theory with numerical experiments, demonstrating how classical optimization can be integrated into engineered quantum strategic interactions.

By Alireza Habibi, Setareh Maghsudi
agents
More like this →
arXiv AI
Sep 10

Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks

The paper introduces Feedback‑Enriched Environments (FEEs) as a new approach to training large language models as autonomous agents for long‑horizon tasks. By shifting from action guidance to observation enrichment during later stages of exploration, FEEs improve performance across SciWorld and BFCL benchmarks with various Qwen3 model scales and RL algorithms. The study shows that FEEs stabilize training, promote proactive exploration, embed environmental guidance into policy weights, and highlight intra‑group feedback consistency as key for stable optimization.

By Hongbang Yuan, Zhuoran Jin, Yixin Cao
llmsagentsreinforcement-learningfine-tuningefficiencybenchmarks
More like this →
arXiv AI
Sep 10

Explaining AI Agents Through Execution Traces

arXiv:2609.06063v1 Announce Type: new Abstract: AI Agents are increasingly deployed in real-world settings, where they interact with external tools and make sequential decisions with limited human ov...

By Vittoria Vineis, Fabiano Veglianti, Lorenzo Antonelli, Claudia Di Carlo, Matteo Silvestri, Gabriele Tolomei
llmsagentsbenchmarks
More like this →