Skip to content
Oct 13 · Tuesday

All papers

Found 670 papers
Filter5

Attack type

Jailbreaks40Prompt injection217Poisoning and backdoors95Extraction and theft9Detection evasion10Denial of service5Malicious use12

Attack technique

Gradient and representation optimization14Automated search51Multi-turn escalation8Encoding and obfuscation16Role-play and persuasion3Reasoning-chain manipulation5Cross-modal payloads11Defense-targeted20Dormant triggers39Selection manipulation11

Model risks

Deception and scheming39Reward hacking31Misalignment and value divergence22Dangerous agent actions85Dangerous capabilities24Inappropriate refusal9Hallucination and fabrication13

Defense type

Model hardening23Inference-time intervention10Detection and filtering42Instruction–data separation49Permissions and approval69Monitoring and auditing43Watermarking and provenance5

Impact

Harmful content32Unauthorized actions219Data and privacy leaks57Output manipulation104Availability and reliability53Oversight failure57Increased misuse capability14

System type

Models and APIs889LLM applications146AI Agent670coding agent140science agent32web agent34Browser and computer use19Multi-agent systems83Embodied systems and robotics47

Attacker access

Black-box21White-box4

Attack surface / entry point

User input107Web pages and interfaces66Documents and messages63Tool responses104Tool and skill descriptions63Code repositories and dependencies28Retrieval corpus11Memory writes43Inter-agent messages28Images, audio and video20Training data7Weights and gradients8Distribution channels49

Layer

Prompt layer11Model layer24Application layer605Training and data layer28

System component

MCP and skills82Memory79RAG10Guardrails and judges50Monitors64Reasoning chains17Permissions and sandboxing91Fine-tuning and open weights8Vision30Audio3Multimodal34
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
System type：AI AgentSystem type：coding agentSystem type：science agentSystem type：web agentSystem type：Embodied systems and roboticsClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  1. OtherarXiv 2610.13912

    RSI-Anything: Unlocking Recursive Self-Improvement with World Models

    Proposes RSI-Anything, which uses a world model to select candidates and retain policy updates.

    arXiv
    2610.13912
    Published
    Layer
    Application layer
    Setting
    coding agent, Browser and computer use
    Evaluated models
    ReasonFlux-Coder-7B, 4B policy, W1
    AbstractRSI-Anything integrates world models into recursive self-improvement through prediction, feedback, and retention checks, and reports gains across multiple domains.

    RSI-Anything is a cross-domain framework: it uses world model predictions to decide which candidates to take external feedback for, then uses the feedback to decide whether the policy, workflow, or predictor is updated, and uses checks to decide which pair is retained. The difficulty to address is the limited interaction budget, and the fact that once the policy changes, the candidate distribution faced by the predictor also changes. The authors argue that improving only one side does not guarantee that the assembled system will be better.

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2610.13710

    OpenSocialJax: Evaluating Social Adaptation in Sequential Social Dilemmas with Open-Ended Environment Dynamics

    Evaluating multi-agent adaptation in social dilemmas with hidden rules using OpenSocialJax

    arXiv
    2610.13710
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-6-Luna, GPT-6-Sol, Claude Opus 5.5 and others8
    AbstractThe authors report that rule discovery often improves payoffs, but public good cleaning becomes concentrated, and shared resources are eventually depleted.

    OpenSocialJax evaluates whether LLMs can simultaneously adapt to unfamiliar environmental mechanisms and other agents in sequential social dilemmas.

    Paper analysisRead analysis
  5. OtherarXiv 2610.13491

    EviRepair: Evidence-Driven Agents for Reliable Vulnerability Repair

    Proposing EviRepair, an evidence-driven multi-agent framework for repository-level vulnerability repair

    arXiv
    2610.13491
    Published
    Layer
    Application layer
    Setting
    coding agent, Multi-agent systems
    Evaluated models
    DeepSeek-V4.1-Flash, GLM-5.2, Qwen3.8-27B
    AbstractEviRepair uses a reviewed vulnerability model for repository-level repair.

    EviRepair is a repository-level automated vulnerability repair framework for sparse vulnerability reports, using a reviewed vulnerability model to separate diagnosis from patch synthesis.

    Paper analysisRead analysis
  6. OtherarXiv 2610.13479

    A local agentic AI framework generates edge-case scenarios for safety assurance

    Proposes a local dual-model closed loop to generate edge scenarios for autonomous system safety assurance

    arXiv
    2610.13479
    Published
    Layer
    Application layer
    Setting
    LLM applications, Embodied systems and robotics
    Evaluated models
    PPO
    AbstractLocal closed-loop generation of JSON edge cases.

    The authors built a local agentic loop that runs on a laptop to generate edge cases for safety arguments of autonomous systems, rather than releasing a new public test set.

    Paper analysisRead analysis
  8. OtherarXiv 2610.13372

    Toward Safe World Models: Risks, Defenses, and Evaluation

    A survey of risks, defenses, and evaluation in the six-stage lifecycle of world models

    arXiv
    2610.13372
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics
    AbstractSafety is written as a property of the prediction-decision closed loop; claims must be linked to observed consequences and versions.

    World model safety is organized by the nature of the prediction-decision loop, not by isolated prediction scores.

    Paper analysisRead analysis
  12. Risky behaviorarXiv 2610.12822

    Reward hacking as a transmissible strategy in multi-agent coding systems

    Show that reward hacking can propagate through code, memory, and plans in multi-agent coding systems

    arXiv
    2610.12822
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Evaluated models
    Qwen2.5-Coder-14B, Gemma-3-12B, Qwen2.5-Coder-7B and others16
    AbstractThe authors state that reward hacking can spread across models and affect routing and aggregation, and that review can reduce delivery.

    Reward hacking induced by coding RL can leave the source agent and enter subsequent collaboration and system coordination.

    Paper analysisRead analysis
  13. OtherarXiv 2610.12756

    How hardware bit flips affect LLM agents: safety and alignment behavior can vary

    Measuring the impact of random weight bit flips on LLM agent safety and alignment behavior

    arXiv
    2610.12756
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen3.6-27B, Qwen3.8-27B, Granite4.1-30B
    AbstractTwo-bit weight faults can be partially repaired in closed-loop settings, but they increase output tokens and, in specific models and scenarios, change safety or alignment behavior.

    After random two-bit weight faults enter an LLM agent, model-level damage becomes recoverable, increased cost, subtle semantic errors, and changes in safety or alignment behavior.

    Paper analysisRead analysis
  14. Evaluation and benchmarksarXiv 2610.12569

    SWE-Duel: Toward a Self-Expanding Arena for Coding Agents

    Proposes SWE-Duel, which lets coding agents mutually evaluate, create problems, and blindly review fixes during evaluation.

    arXiv
    2610.12569
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.5, Claude Opus 4.8, Kimi K2.7 Code and others11
    AbstractThe mutual evaluation arena creates questions during evaluation.

    SWE-Duel is a coding agent arena that generates tasks and judges only at evaluation time, to avoid leakage and saturation of static benchmarks.

    Paper analysisRead analysis
  17. Analysis and theoryarXiv 2610.12436

    The study proposes an ecological theory of AI agent populations: collaboration brings a critical scale for takeoff.

    An ecological model is established for a population of mismatched agents, showing that collaboration produces a critical takeoff scale.

    arXiv
    2610.12436
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    AbstractThe authors say that collaboration changes takeoff from an individual capability threshold to a population threshold, so small-population evaluations are insufficient.

    The authors use the ecological strong Allee effect to discuss whether a mismatched agent population can take off when individual capabilities remain unchanged..

    Paper analysisRead analysis
  18. DefensesarXiv 2610.12432

    FAITH: A feasibility-aware safety filtering reinforcement learning framework for high-dimensional systems

    Proposes the FAITH safe filtering reinforcement learning framework, training high-dimensional systems to optimize task reward under constraints

    arXiv
    2610.12432
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    AbstractFAITH separates safety filtering from reward optimization.

    FAITH is a model-free safe filtering reinforcement learning framework for high-dimensional systems: safety correction and task reward reside in separate modules.

    Paper analysisRead analysis
  20. Evaluation and benchmarksarXiv 2610.12360

    The paper proposes the ISE framework to evaluate LLM agents' epistemic humility under knowledge conflicts

    Proposes the ISE framework to evaluate the epistemic humility of LLM agents under knowledge conflicts

    arXiv
    2610.12360
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Nemotron-Orchestrator-8B, Claude Sonnet 4.6, GPT-5 and others5
    AbstractISE trajectory evaluations show that high task accuracy across four agents does not correspond to higher cognitive humility.

    What the authors want to test is not whether the agent's final answer is correct, but whether, when a knowledge conflict arises, it recognizes the gap in its trajectory, performs bounded tool follow-up, and writes the unresolved uncertainty to the user.

    Paper analysisRead analysis
Load more