Large language model (LLM) agents can now carry out long-horizon technical workflows involving complex tool use, code execution, file edits, and generated artifacts. As agents do more work faster, the productivity bottleneck shifts from producing outputs to auditing whether those outputs are correct and trustworthy. Agent observability systems make fine-grained execution events visible, but visibility alone still leaves reviewers to reconstruct which actions, artifacts, and validation steps matter for a particular conclusion. We introduce LEDGER - Layered Evidence and Decision Graphs for Execution Review, a tracing and review system that builds layered trace graphs over observed agent sessions. LEDGER preserves Trace Records while grouping them into Evidence Nodes and Workflow Nodes, representing artifacts as evidence anchors, and adding typed semantic edges that connect claims to supporting actions, artifacts, and checks. Through data-analysis and coding examples, we show how the resulting traces expose workflow decisions, artifact lineage, repair steps, validation coverage, and claim-support paths for evidence-centered audit.
An automated gap analysis shows the architecture demonstrates alignment with five of eight requirements derived from the EU AI Act and FDA AI/ML guidance, and module-level evaluations of claim extraction, evidence binding, and silent-edit detection are reported together with a measured baseline comparison on retraction...
Tracekit is an open-source, dependency-free system that captures three channels for every agent session: what the human asked (intent), what the model said of its reasoning (self-report), and what it actually executed (actions).
LLM-based agents are increasingly used as action-taking systems that operate over files, databases, networks, and external services. In this setting, safety failures can become unauthorized world effects, such as data deletion, protected-resource modification, or secret exfiltration, rather than merely unsafe text outp...
Jun-Hao Zhou, Tao Jia· Proceedings of the 41st IEEE...· 0 citations
Agent-to-Agent (A2A) communication enables large language model (LLM) agents to exchange tasks, messages, and artifacts across organizations. A valid message alone does not establish that a final workflow claim is supported by a complete, ordered, and case-consistent evidence path. We present A2A-CaseVerify, a determin...
Repository-level repair requires not only correct patches but also inspectable records that explain how issue requirements are translated into code changes and post-edit evidence. We contribute THEMIS, a stage-aware repair workflow that externalizes this requirement-to-repair process through semantic interpretation, a...
Tool-using large language model (LLM) agents turn generated text into real side effects, so poisoned tool metadata, retrieved pages, memory, and reusable skills can steer the next call. Vetting an artifact before admission does not settle this. A safe variant and a leaking variant can produce the same admission evidenc...
Feng-Peng Li, Qi-Zhou Wang, Yu-Ke Hu et al.· 0 citations
Known for his clear and elegant writing style, Bertsekas shaped fields from control and optimization to large-scale computation and artificial intelligence.
MIT News · Artificial Intelligence· news.mit.eduJul 7, 2026
The professor of physics and inaugural director of the NSF AI Institute for Artificial Intelligence and Fundamental Interactions will lead LNS and continue his research in particle physics.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
