Search: “agents”

arXiv:2607.09770v2 Announce Type: replace Abstract: Industrial agentic AI systems increasingly exhibit a gap between prototype capability and production deployment. In particular, adaptive agents may

arXiv:2609.10248v1 Announce Type: cross Abstract: Traditional software delivery assumes a static paradigm: code is constructed prior to execution and deployed as a fixed artifact. We present Agentic J

arXiv:2609.10901v1 Announce Type: new Abstract: LLM search agents are often evaluated on final-answer accuracy, overlooking the process. Analyzing a search strategy requires understanding how credible

arXiv:2609.05995v1 Announce Type: new Abstract: Achieving reliable autonomy in the wild requires agents to sustain continuous operations across long-horizon trajectories. However, as agents navigate t

Amazon.com Inc. announced today that Quick, the company’s artificial intelligence assistant and enterprise platform for AI agents, is now generally available on macOS and Windows. The agentic platform

arXiv:2609.05736v2 Announce Type: new Abstract: LLM tool agents can be improved without retraining by modifying the runtime harness around a fixed model: prompts, tool interfaces, middleware, state ha

If you ask a coding agent to write a program that maps x to y given some (x, y) examples, you're doing a very expensive form of symbolic learning. In fact what you're doing is specifically a form of D

Recommended read. Interaction horizon scheduling is an underexplored control problem in agentic RL This paper from the Qwen team takes a closer look at the problem. Scaling the maximum number of envir

arXiv:2609.05920v1 Announce Type: cross Abstract: Agent Skills combine instructions with files, packages, tools, models, and services, so operational identity can exceed a signed directory. Recursive

I like this framing a lot: agent improvement is harness improvement, not model improvement The interesting interventions are often at the tool boundary: - what context you pass - when tools are provid

we broke down the full open model stack for agentic coding and how to swap each layer independently model → inference → gateway/router → harness → tools the stack stays flexible as better models, prov

arXiv:2609.04298v1 Announce Type: new Abstract: Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We

Sometimes I wonder what would have happened if we hadn't disclosed the agent cyberattack publicly. It reinforced my conviction that we need 100x more transparency in AI. Otherwise we're going to be in

Banger paper from Tencent on environment evolution. Environment supply is becoming the main limit on agent RL. So this is worth a read. (bookmark it) Agent RL needs a steady supply of environments har

arXiv:2609.03787v1 Announce Type: new Abstract: AI agents increasingly gather evidence, invoke tools, apply constraints, and produce decisions that people or software may commit to action. A final out

arXiv:2609.03667v1 Announce Type: cross Abstract: Generalising to unseen tasks remains a fundamental challenge in offline multi-agent reinforcement learning (MARL). In this work, we present a principl

arXiv:2609.02967v1 Announce Type: cross Abstract: Topology-guided safeguards for LLM-based multi-agent systems (MAS) train a GNN over the inter-agent communication graph to localize risky agents and i

arXiv:2609.01437v1 Announce Type: cross Abstract: As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external execution infrastructure, commonly

arXiv:2202.06853v2 Announce Type: cross Abstract: To help facilitate a variety of simulations related to healthcare facilities in North Carolina, we have developed an agent-based model (ABM) to accura

arXiv:2608.30373v1 Announce Type: new Abstract: Multi-Agent Debate (MAD) has been widely adopted to improve LLM-based evaluation by prompting multiple agents to negotiate and reach a consensus. Howeve

arXiv:2608.30192v1 Announce Type: new Abstract: Traditional finance relies on experts to hand-craft factors through a principled process grounded in economic rationale. Recent LLM-based multi-agent sy

The post explains how a quick, one‑hour audit of AI agent usage revealed $1 million per year in avoidable spend. By reviewing deployment patterns and trimming unnecessary calls, the team reallocated r

“increasing agent autonomy can gradually make human oversight ineffective by causing approval fatigue, overreliance, loss of situational awareness, and skill degradation.” new paper from @mmitchell_ai

arXiv:2608.28624v1 Announce Type: cross Abstract: Accurate interpretation of single-visit and longitudinal clinical assessments for Parkinson's disease is time-consuming and often depends on specialis

arXiv:2608.29526v1 Announce Type: new Abstract: Academic reviews, scholarly commentaries, and book reviews serve as sources of evaluative statements about theories, methods, literature, institutions,

💯: “as the lines get blurred, we lose our ability to pinpoint the technically-grounded points of leverage in AI agent oversight” This is a *super exciting* read. It's like a sci-fi thriller. And that'

“Not so much agent civilizations doing crazy things as OpenAI ignoring fundamental security prectices as it turned out.” Good article. I wrote a detailed technical analysis from a security engineering

we are rolling support for the new MCP spec in langchain and need feedback on our new API! with this new pattern you connect langchain agents to multiple MCP servers, hook up oauth, use elicitation w/

Finally, a paper testing whether hiding your agent skill files actually protects them. The short answer is no. That's concerning. Worth reading if you sell access to a skill or share one across teams.

arXiv:2608.26895v1 Announce Type: cross Abstract: Agentic recommender systems ground each decision of a large language model (LLM) in a persistent memory of the user, and in existing agents that memor

arXiv:2608.26004v1 Announce Type: cross Abstract: Agentic LLM pipelines face escalating inference costs as context accumulates across retrieval, tool use, and multi-turn interactions. To control laten

We ran Signal on Alyx, the AI engineering agent built into Arize AX. It surfaced a duplicate task-state loop and a 43-call dataset retry that appeared as valid tool activity or an OK root span. The po

arXiv:2608.24103v1 Announce Type: new Abstract: Commercial design platforms increasingly edit documents through large language model (LLM) agents, but two practical problems block reliable deployment:

Amazon Bedrock AgentCore Evaluations decouples agent evaluation from the framework you build on. As long as your agent emits OpenTelemetry telemetry, the service can score it, whether you use LangGrap

arXiv:2608.22132v1 Announce Type: cross Abstract: Biomedical multi-hop question answering (QA) requires models to connect evidence across intermediate entities such as diseases, drugs, proteins, and p

arXiv:2601.04786v3 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) enable agentic systems trained with reinforcement learning (RL) over multi-turn interaction, b

arXiv:2608.21159v1 Announce Type: cross Abstract: Tool-using AI agents turn delegated tasks into provider effects, yet authorization often ends at admission while provider state, delivery, retry, and

arXiv:2608.20342v1 Announce Type: new Abstract: Large language model (LLM) coding agents start each session with an empty context window, discarding accumulated knowledge from prior work. We present P

arXiv:2608.20786v1 Announce Type: new Abstract: Multi-agent pipelines that author formal documents must both read a requester's forms and write against them. We report a deployed tender-response syste

arXiv:2608.19901v1 Announce Type: cross Abstract: Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration. This creates a

arXiv:2608.20099v1 Announce Type: cross Abstract: LLM-based Multi-Agent Systems (MAS) achieve strong performance on complex reasoning tasks by coordinating multiple agents, but at the cost of substant

arXiv:2608.18677v1 Announce Type: new Abstract: Amid concerns that generative AI may standardize art interpretation, this paper examines whether LLM-based interaction can support plural art-historical

arXiv:2608.17071v1 Announce Type: new Abstract: We present KernelArc, a multi-agent framework for autonomous GPU kernel optimization across heterogeneous workloads. Strategy-specialized agents run in

arXiv:2608.16891v1 Announce Type: new Abstract: Agentic AI systems request tool actions that can modify files, send messages, launch jobs, or change workflow state. This shifts the safety problem from

arXiv:2608.14035v1 Announce Type: new Abstract: Recent developments in large language models (LLMs) and tool-using agents encourage people to explore the potential of using agents in chip design. The

arXiv:2608.11338v1 Announce Type: new Abstract: Recently, the practice of augmenting LLM agent capability with skills has gained prevalence. We explore the cost effective adaptation of agents to novel