arXiv AI
Jul 15
Tracing Agentic Failure from the Flow of Success
arXiv:2607. 12747v1 Announce Type: new Abstract: Failure attribution for LLM-based agentic systems, i.
Do Agents Know When They Succeed? Calibrating Agent Confidence from Internal Representations
The paper examines whether internal representations of agentic systems can better indicate task success than traditional confidence measures. It introduces two methods—Latent Trajectory Dynamics (LTD) and Action Representation Probe (ARP)—that analyze changes in residual-stream representations and action-level representations, respectively. Experiments on Bash, SQL, and Python benchmarks with Qwen and DeepSeek models show these methods outperform conventional surface-level and sequence-based calibration baselines, offering a zero‑overhead reliability monitor without prompt changes or multiple rollouts.
Related stories
arXiv Machine Learning
Sep 1
Last Step Matters: Early Uncertainty Cannot Predict Failure in Long-Horizon Agents
arXiv:2608.29685v1 Announce Type: new Abstract: Early failure prediction is important for long-horizon agents, as it enables timely intervention and can reduce inference and tool-use costs. Uncertain...
arXiv AI
Jun 2
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
arXiv:2603. 14465v2 Announce Type: replace Abstract: While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions.
arXiv AI
Sep 1
AgentRx: Diagnosing AI Agent Failures from Execution Trajectories
arXiv:2602.02475v2 Announce Type: replace Abstract: AI agents often fail in ways that are difficult to localize because executions are probabilistic, long-horizon, multi-agent, and mediated by noisy...
arXiv AI
Aug 18
From Sequence to Structure: Relational Uncertainty Propagation for LLM Agents
The paper introduces RUPA, a trajectory‑level uncertainty quantification framework for large language model agents. RUPA models an agent’s execution as a directed graph of reasoning states, tool interactions, and environment feedback, then propagates uncertainty across this graph to capture long‑range dependencies. Experiments on benchmarks such as τ‑2, Terminal‑Bench‑2, and GAIA show that RUPA outperforms existing methods, enabling earlier failure detection and more reliable agent execution.
arXiv AI
Oct 15
Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents
arXiv:2610.18614v1 Announce Type: new Abstract: Controlling an acting LLM agent means deciding, at each step of a long-horizon task, whether to trust its next action, abstain, or hand off to a human....
arXiv Computation and Language
Oct 12
ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation
The paper introduces ARTIS, a framework that separates exploration from commitment by using iterative simulation to test large language model actions before real-world execution. This approach extends inference-time computation to boost action-level reliability and robustness while avoiding environmental risk. The authors also highlight that standard LLM simulators miss rare, high-impact failures, and propose a risk‑aware simulator that focuses on fidelity for failure‑inducing actions, showing significant reliability gains across agentic benchmarks.
arXiv AI
Jul 8
Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents
arXiv:2510. 19771v4 Announce Type: replace Abstract: LLM-based agents are increasingly moving towards proactivity: rather than awaiting instruction, they exercise agency to anticipate user needs and solve them autonomously.
arXiv AI
Oct 28
PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement
PIVOT (Plan-Inspect-eVOlve Trajectories) is a self‑supervised framework that refines large‑language‑model agent plans by treating trajectories as optimizable objects. It operates in four stages—PLAN, INSPECT, EVOLVE, and VERIFY—using structured losses and textual gradients to iteratively improve trajectories and ensure compliance with task constraints. Experiments on DeepPlanning and GAIA show that PIVOT achieves up to 94% relative improvement in constraint satisfaction with human‑in‑the‑loop feedback and still delivers significant gains autonomously, while using 3x to 5x fewer tokens than competing methods.
arXiv AI
Sep 24
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
The paper introduces VHD-Play, a pipeline that first samples and solves a mathematical model before generating agentic reinforcement learning environments, ensuring that dynamics and evaluation are aligned from the outset. This approach yields 3,300 diverse environments at a low cost and significantly improves the performance of a large language‑model agent (Qwen3.6‑35B‑A3B) across multiple diagnostic families and external benchmarks. The study demonstrates that stateful interaction is a key factor in learning gains and that scaling the training substrate can further enhance performance.
arXiv Machine Learning
Sep 22
TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling
arXiv:2605.27690v2 Announce Type: replace-cross Abstract: LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate st...
arXiv AI
Jun 2
From Features to Actions: Explainability in Traditional and Agentic AI Systems
arXiv:2602. 06841v4 Announce Type: replace Abstract: Over the last decade, Explainable AI has primarily focused on interpreting individual model predictions, producing post-hoc explanations that relate inputs to outputs under a fixed decision structure.