most citedALAS: A Stateful Multi-LLM Agent Framework for Disruption-Aware Planning

3 citations · 6 across the 5 of their papers we have counts for

collaborators
Showing cs.AIShow all

8 papers · 1 filter

cs.AI2026

Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows

Edward Y. Chang, Longling Geng

LLMs increasingly generate workflow actions and repairs that may be well formed yet stale, infeasible, conflicting, or destructive of their own evidence. We introduce Agentic Trans…

cs.AI2026

TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized Views

Edward Y. Chang

World models let agents plan against predicted physical state, but that state drifts; re-observation is costly and delayed, and repair can fail. We present TRACE-RealWorld (TRW), t…

cs.AI20263 cited

CausalT5k: Diagnosing Refusal and Failure Modes in Trustworthy Causal Reasoning Across Causal Rungs

Longling Geng, Andy Ouyang, Theodore Wu +10

Large language models increasingly produce fluent causal explanations, yet they often fail in ways aggregate accuracy cannot diagnose: confusing association with intervention, aban…

cs.AI20262 cited

RAudit: A Blind Auditing Protocol for Large Language Model Reasoning

Edward Y. Chang, Longling Geng

Inference-time scaling can amplify reasoning pathologies: sycophancy, rung collapse, and premature certainty. We present RAudit, a diagnostic protocol for auditing LLM reasoning wi…

cs.AI20253 cited

ALAS: A Stateful Multi-LLM Agent Framework for Disruption-Aware Planning

Edward Y. Chang, Longling Geng

Large language models (LLMs) excel at rapid generation of text and multimodal content, yet they falter on transaction-style planning that demands ACID-like guarantees and real-time…

cs.AI20252 cited

SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning

Edward Y. Chang, Longling Geng

This paper introduces SagaLLM, a structured multi-agent architecture designed to address four foundational limitations of current LLM-based planning systems: unreliable self-valida…