PROBE turns runtime telemetry from failed software engineering agent runs into evidence-grounded diagnoses and actionable recovery guidance, achieving 65.37% diagnosis accuracy and 21.79% recovery rate on 257 cases.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
baseline 1
dataset 1
citation-polarity summary
representative citing papers
The manuscript body introduces PokeGym, a vision-only automated 3D-game benchmark, while the abstract claims a G-EvoMAC method and 60.18% success rate absent from the body.
DoubleAgents shows that a distributed-cognition design with coordination agent, dashboard, and policy module increases user comfort and reliance on AI agents for coordination tasks over time.
CUGA introduces a runtime governance architecture that enforces policies at five checkpoints in generalist agent execution pipelines for predictable and compliant behavior.
RAC is a log-based recovery paradigm implemented as an architectural extension to agent frameworks, achieving 1.5-8X better latency and token economy than LLM-based recovery on τ-bench and REALM-Bench.
Agent Mentor analyzes semantic trajectories in agent logs to identify undesired behaviors and derives corrective prompt instructions, yielding measurable accuracy gains on benchmark tasks across three agent setups.
RLVR training on five synthetic Atlassian API environments raises average tool-use reward for Qwen models from 0.35-0.92 to 0.95-1.00 on four non-degenerate scenarios.
citing papers explorer
-
Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents
PROBE turns runtime telemetry from failed software engineering agent runs into evidence-grounded diagnoses and actionable recovery guidance, achieving 65.37% diagnosis accuracy and 21.79% recovery rate on 257 cases.
-
Mastering PokeGym: Graph-Guided Multimodal Evolution at Test Time
The manuscript body introduces PokeGym, a vision-only automated 3D-game benchmark, while the abstract claims a G-EvoMAC method and 60.18% success rate absent from the body.
-
DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow
DoubleAgents shows that a distributed-cognition design with coordination agent, dashboard, and policy module increases user comfort and reliance on AI agents for coordination tasks over time.
-
Governance by Construction for Generalist Agents
CUGA introduces a runtime governance architecture that enforces policies at five checkpoints in generalist agent execution pipelines for predictable and compliant behavior.
-
Robust Agent Compensation (RAC): Teaching AI Agents to Compensate
RAC is a log-based recovery paradigm implemented as an architectural extension to agent frameworks, achieving 1.5-8X better latency and token economy than LLM-based recovery on τ-bench and REALM-Bench.
-
Agent Mentor: Framing Agent Knowledge through Semantic Trajectory Analysis
Agent Mentor analyzes semantic trajectories in agent logs to identify undesired behaviors and derives corrective prompt instructions, yielding measurable accuracy gains on benchmark tasks across three agent setups.
-
Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows
RLVR training on five synthetic Atlassian API environments raises average tool-use reward for Qwen models from 0.35-0.92 to 0.95-1.00 on four non-degenerate scenarios.