DART is a modular runtime that certifies semantically recoverable boundaries for failed tool-agent instances and selects admissible restore points that preserve downstream commitments or blocks recovery.
hub
Agentrx: Diagnosing AI agent failures from execution trajectories,
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
background 3
baseline 1
citation-polarity summary
years
2026 14representative citing papers
A span-decomposed evaluation framework for AI agents achieves state-of-the-art results on GAIA and SWE-Bench with up to 3.5x gains in localization accuracy by breaking traces into independent per-span judgments.
Hidden-state probes can flag doomed LLM-agent episodes from the first round, and a recall-calibrated cascade of abort gates cuts generated tokens by up to 60% while preserving a chosen success-recall target.
TraceProbe normalizes coding agent trajectories into canonical actions and applies rule-based detectors to localize failure patterns and behavioral divergences that resolve rate hides.
High-velocity agentic coding becomes governable when engineers convert recurring structural failures into durable, machine-actionable governance mechanisms rather than relying on continuous human code review.
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.
ContextCov compiles agent instruction files into static, runtime, and architectural guardrails, raising constraint compliance to 88.3% on SWE-bench Lite tasks versus 67% and 50.3% for prompt and reflection baselines.
GRADE models any LLM agent run as a graph with execution and graded dependency edge layers to enable failure prediction and fault localization across tool, coding, and web agent corpora.
Insights Generator is a multi-agent system that produces evidence-backed insights from corpora of LLM agent traces and yields 30.4pp performance gains when humans apply the reports.
SkillsVote is a governance system for agent skills that profiles corpora, recommends via search, and gates updates on successful reusable outcomes, yielding benchmark gains without model changes.
An external controller for frozen LLMs raises strict validation success on three RL coding tasks from 0/9 to 8/9 by selecting memory records and skills, running fail-fast checks, and propagating credit via eligibility traces.
PBKV predicts agent invocations in dynamic LLM workflows to manage KV-cache reuse, delivering up to 1.85x speedup over LRU and 1.26x over KVFlow.
A new algorithm learns correct agent behavior models from few traces by combining dominator analysis, LLMs, and automata to validate sequential executions with high accuracy.
citing papers explorer
-
DART: Semantic Recoverability for Structured Tool Agents
DART is a modular runtime that certifies semantically recoverable boundaries for failed tool-agent instances and selects admissible restore points that preserve downstream commitments or blocks recovery.
-
Holistic Evaluation and Failure Diagnosis of AI Agents
A span-decomposed evaluation framework for AI agents achieves state-of-the-art results on GAIA and SWE-Bench with up to 3.5x gains in localization accuracy by breaking traces into independent per-span judgments.
-
Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade
Hidden-state probes can flag doomed LLM-agent episodes from the first round, and a recall-calibrated cascade of abort gates cuts generated tokens by up to 60% while preserving a chosen success-recall target.
-
What Resolve Rate Hides: Trajectory Structure Diagnostics for Coding Agents
TraceProbe normalizes coding agent trajectories into canonical actions and applies rule-based detectors to localize failure patterns and behavioral divergences that resolve rate hides.
-
Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering
High-velocity agentic coding becomes governable when engineers convert recurring structural failures into durable, machine-actionable governance mechanisms rather than relying on continuous human code review.
-
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.
-
ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files
ContextCov compiles agent instruction files into static, runtime, and architectural guardrails, raising constraint compliance to 88.3% on SWE-bench Lite tasks versus 67% and 50.3% for prompt and reflection baselines.
-
GRADE: Graph Representation of LLM Agent Dependency and Execution
GRADE models any LLM agent run as a graph with execution and graded dependency edge layers to enable failure prediction and fault localization across tool, coding, and web agent corpora.
-
Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents
Insights Generator is a multi-agent system that produces evidence-backed insights from corpora of LLM agent traces and yields 30.4pp performance gains when humans apply the reports.
-
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
SkillsVote is a governance system for agent skills that profiles corpora, recommends via search, and gates updates on successful reusable outcomes, yielding benchmark gains without model changes.
-
PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents
An external controller for frozen LLMs raises strict validation success on three RL coding tasks from 0/9 to 8/9 by selecting memory records and skills, running fail-fast checks, and propagating credit via eligibility traces.
-
Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management
PBKV predicts agent invocations in dynamic LLM workflows to manage KV-cache reuse, delivering up to 1.85x speedup over LRU and 1.26x over KVFlow.
-
Learning Correct Behavior from Examples: Validating Sequential Execution in Autonomous Agents
A new algorithm learns correct agent behavior models from few traces by combining dominator analysis, LLMs, and automata to validate sequential executions with high accuracy.
- Auditable Agents