Entity · paper

From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization

paperactiveprovisionalfrom-noisy-traces-to-root-causes-structural-trajectory-analysis-and-causal-extraction-for-agent-optimization-268f537f·1 events·first seen 4d ago

Aliases: From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization

Co-occurring entities

VeruSAGE-Bench STRACE

More like this (12)

What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates Behavioral Trajectory Tracking Framework From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents From Application-Layer Simulation to Native Meta-Architecture: Structural Tension as an Endogenous Driver for Heterogeneous AI Evolution Structural Causal Model Multi-Turn Evaluation of Deep Research Agents Under Process-Level Feedback Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models Reward Modeling for Multi-Agent Orchestration APPO: Agentic Procedural Policy Optimization Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision Graph-Regularized Agentic Context Evolution A Systematic Approach for Selecting Trajectories for Data Augmentation

Recent events (1)

5arXiv · cs.CL·4d ago·source ↗

STRACE framework improves LLM agent optimization via structural trajectory analysis and causal extraction

Researchers introduce STRACE (Structural TRajectory Analysis and Causal Extraction), a framework for constructing high signal-to-noise optimization contexts for long-horizon LLM agents. At the batch level, STRACE mines failure patterns to filter redundant traces; within each trace, it performs causal localization over a textual dependency graph to isolate root-cause steps. On the formal verification benchmark VeruSAGE-Bench, STRACE achieves a 1.4× success-rate improvement (42.5% to 58.5%) over human-expert-designed agents, outperforming standard context-filtering baselines.

Evaluation and Benchmarking Agent and Tool Ecosystem VeruSAGE-Bench From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization STRACE