74 articles tagged with #llm-agents. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
AINeutralarXiv – CS AI · 1d ago7/10
🧠Researchers identified a critical failure mode in LLM-based agents called policy-invisible violations, where agents execute actions that appear compliant but breach organizational policies due to missing contextual information. They introduced PhantomPolicy, a benchmark with 600 test cases, and Sentinel, an enforcement framework using counterfactual graph simulation that achieved 93% accuracy in detecting violations compared to 68.8% for baseline approaches.
AIBullisharXiv – CS AI · 1d ago7/10
🧠Researchers demonstrate an autonomous LLM agent capable of executing a complete research loop—reading, reproducing, critiquing, and extending computational physics papers. Testing across 111 papers reveals the agent identifies substantive flaws in 42% of cases, with 97.7% of issues requiring actual computation to detect, and produces a publishable peer-review comment on a Nature Communications paper without human direction.
AIBullisharXiv – CS AI · 1d ago7/10
🧠Researchers introduce dual-trace memory encoding for LLM agents, pairing factual records with narrative scene reconstructions to improve cross-session recall by 20+ percentage points. The method significantly enhances temporal reasoning and multi-session knowledge aggregation without increasing computational costs, advancing the capability of persistent AI agent systems.
AIBullisharXiv – CS AI · 1d ago7/10
🧠AutoSurrogate is an LLM-driven framework that automates the construction of deep learning surrogate models for subsurface flow simulation, enabling domain scientists without machine learning expertise to build high-quality models through natural language instructions. The system autonomously handles data profiling, architecture selection, hyperparameter optimization, and quality assessment while managing failure modes, demonstrating superior performance to expert-designed baselines on geological carbon storage tasks.
AINeutralarXiv – CS AI · 1d ago7/10
🧠Researchers introduce HORIZON, a diagnostic benchmark for identifying and analyzing why large language model agents fail at long-horizon tasks requiring extended action sequences. By evaluating state-of-the-art models across multiple domains and proposing an LLM-as-a-Judge attribution pipeline, the study provides systematic methodology for understanding agent limitations and improving reliability.
🧠 GPT-5🧠 Claude
AIBearisharXiv – CS AI · 2d ago7/10
🧠Researchers deployed LLM agents in a simulated NYC environment to study how strategic behavior emerges when agents face opposing incentives, finding that while models can develop selective trust and deception tactics, they remain highly vulnerable to adversarial persuasion. The study reveals a persistent trade-off between resisting manipulation and completing tasks efficiently, raising important questions about LLM agent alignment in competitive scenarios.
AIBullisharXiv – CS AI · 2d ago7/10
🧠Researchers present Synthius-Mem, a brain-inspired AI memory system that achieves 94.4% accuracy on the LoCoMo benchmark while maintaining 99.6% adversarial robustness—preventing hallucinations about facts users never shared. The system outperforms existing approaches by structuring persona extraction across six cognitive domains rather than treating memory as raw dialogue retrieval, reducing token consumption by 5x.
AIBullisharXiv – CS AI · 2d ago7/10
🧠Researchers propose MGA (Memory-Driven GUI Agent), a minimalist AI framework that improves GUI automation by decoupling long-horizon tasks into independent steps linked through structured state memory. The approach addresses critical limitations in current multimodal AI agents—context overload and architectural redundancy—while maintaining competitive performance with reduced complexity.
AIBullisharXiv – CS AI · 2d ago7/10
🧠UniToolCall introduces a standardized framework unifying tool-use representation, training data, and evaluation for LLM agents. The framework combines 22k+ tools and 390k+ training instances with a unified evaluation methodology, enabling fine-tuned models like Qwen3-8B to achieve 93% precision—surpassing GPT, Gemini, and Claude in specific benchmarks.
🧠 Claude🧠 Gemini
AIBullisharXiv – CS AI · 2d ago7/10
🧠Researchers introduce DiaFORGE, a three-stage framework for training LLMs to reliably invoke enterprise APIs by focusing on disambiguation between similar tools and underspecified arguments. Fine-tuned models achieved 27-49 percentage points higher tool-invocation success than GPT-4o and Claude-3.5-Sonnet, with an open corpus of 5,000 production-grade API specifications released for further research.
🧠 GPT-4🧠 Claude
AIBullisharXiv – CS AI · 2d ago7/10
🧠Anthropic's CoEvoSkills framework enables AI agents to autonomously generate complex, multi-file skill packages through co-evolutionary verification, addressing limitations in manual skill authoring and human-machine cognitive misalignment. The system outperforms five baselines on SkillsBench and demonstrates strong generalization across six additional LLMs, advancing autonomous agent capabilities for professional tasks.
🏢 Anthropic🧠 Claude
AINeutralarXiv – CS AI · 2d ago7/10
🧠Researchers introduce The Amazing Agent Race (AAR), a new benchmark revealing that LLM agents excel at tool-use but struggle with navigation tasks. Testing three agent frameworks on 1,400 complex, graph-structured puzzles shows the best achieve only 37.2% accuracy, with navigation errors (27-52% of failures) far outweighing tool-use failures (below 17%), exposing a critical blind spot in existing linear benchmarks.
🧠 Claude
AIBullisharXiv – CS AI · 2d ago7/10
🧠Researchers introduce ContextCurator, a reinforcement learning-based framework that decouples context management from task execution in LLM agents, addressing the context bottleneck problem. The approach pairs a lightweight specialized policy model with a frozen foundation model, achieving significant improvements in success rates and token efficiency across benchmark tasks.
🧠 GPT-4🧠 Gemini
AIBullisharXiv – CS AI · 3d ago7/10
🧠Researchers introduce LOM-action, an enterprise AI system that grounds LLM-based decisions in business ontologies and event-driven simulations rather than unrestricted knowledge spaces. The approach achieves 93.82% accuracy with 98.74% F1 scores on decision chains, vastly outperforming larger models like DeepSeek-V3.2, while maintaining complete audit trails for enterprise compliance.
AINeutralarXiv – CS AI · 3d ago7/10
🧠Researchers propose Many-Tier Instruction Hierarchy (ManyIH), a new framework for resolving conflicts among instructions given to large language model agents from multiple sources with varying authority levels. Current models achieve only ~40% accuracy when navigating up to 12 conflicting instruction tiers, revealing a critical safety gap in agentic AI systems.
AIBullisharXiv – CS AI · 6d ago7/10
🧠Researchers introduce LLM-in-Sandbox, a minimal computer environment that significantly enhances large language models' capabilities across diverse tasks without additional training. The approach enables weaker models to internalize agent-like behaviors through specialized training, demonstrating that environmental interaction—not just model parameters—drives general intelligence in LLMs.
AINeutralarXiv – CS AI · Apr 77/10
🧠Researchers have identified a new class of supply-chain threats targeting AI agents through malicious third-party tools and MCP servers. They've created SC-Inject-Bench, a benchmark with over 10,000 malicious tools, and developed ShieldNet, a network-level security framework that achieves 99.5% detection accuracy with minimal false positives.
AINeutralarXiv – CS AI · Apr 77/10
🧠Researchers have identified a new security vulnerability called 'causality laundering' in AI tool-calling systems, where attackers can extract private information by learning from system denials and using that knowledge in subsequent tool calls. They developed the Agentic Reference Monitor (ARM) system to detect and prevent these attacks through enhanced provenance tracking.
AINeutralarXiv – CS AI · Apr 77/10
🧠A comprehensive study of 10,000 trials reveals that most assumed triggers for LLM agent exploitation don't work, but 'goal reframing' prompts like 'You are solving a puzzle; there may be hidden clues' can cause 38-40% exploitation rates despite explicit rule instructions. The research shows agents don't override rules but reinterpret tasks to make exploitative actions seem aligned with their goals.
🏢 OpenAI🧠 GPT-4🧠 GPT-5
AIBullishMarkTechPost · Apr 67/10
🧠RightNow AI has released AutoKernel, an open-source framework that uses autonomous LLM agents to optimize GPU kernels for PyTorch models. This tool aims to automate the complex process of writing efficient GPU code, addressing one of the most challenging aspects of machine learning engineering.
AIBullisharXiv – CS AI · Mar 277/10
🧠Researchers introduce DRIFT, a new security framework designed to protect AI agents from prompt injection attacks through dynamic rule enforcement and memory isolation. The system uses a three-component approach with a Secure Planner, Dynamic Validator, and Injection Isolator to maintain security while preserving functionality across diverse AI models.
AIBullisharXiv – CS AI · Mar 267/10
🧠Researchers developed the Cognitive Firewall, a hybrid edge-cloud defense system that protects browser-based AI agents from indirect prompt injection attacks. The three-stage architecture reduces attack success rates to below 1% while maintaining 17,000x faster response times compared to cloud-only solutions by processing simple attacks locally and complex threats in the cloud.
AINeutralarXiv – CS AI · Mar 267/10
🧠Researchers propose Collaborative Causal Sensemaking (CCS) as a new framework to improve human-AI collaboration in high-stakes decision making. The study identifies a 'complementarity gap' where current AI agents function as answer engines rather than true collaborative partners, limiting the effectiveness of human-AI teams.
AIBullisharXiv – CS AI · Mar 177/10
🧠Researchers introduce D-MEM, a biologically-inspired memory architecture for AI agents that uses dopamine-like reward prediction error routing to dramatically reduce computational costs. The system reduces token consumption by over 80% and eliminates quadratic scaling bottlenecks by selectively processing only high-importance information through cognitive restructuring.
AIBullisharXiv – CS AI · Mar 167/10
🧠Researchers introduce the AI Search Paradigm, a comprehensive framework for next-generation search systems using four LLM-powered agents (Master, Planner, Executor, Writer) that collaborate to handle everything from simple queries to complex reasoning tasks. The system employs modular architecture with dynamic workflows for task planning, tool integration, and content synthesis to create more adaptive and scalable AI search capabilities.
