arXiv subjects

Longling Geng

Publications and source records attributed to Longling Geng.

9 recordsLinked to original sources

arXiv2026

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

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 Transaction Processing (ATP), which treats generated actions as untrusted proposals until deterministic admission accepts them under an executable constraint set C. Its two-sided principle is: a proposal is not truth, and no proposal foresees every disruption. Anything may propose, but only the runtime admits and commits; unforeseen disruptions trigger bounded reactive repair whose output re-enters admission. Mnemosyne realizes ATP with an append-only transition log, effective-state projection, dependency-safe compensation, and active contract records. Under stated assumptions and relative to C, we prove four safety properties (authority separation, serial-equivalent generative admission, evidence-preserving repair, and obligation containment) and establish bounded reactive repair. Across nine safety benchmarks and a four-case Temporal SDK comparison, ATP rejects every targeted violation while admitting valid work. A matched data-size sweep measures 5.2-6.6% incremental throughput cost over the same local durable commit path and exposes local saturation. In a companion scheduling harness, local repair edits nearly an order of magnitude fewer operations than global recompute; a 12-scenario interruption stress test rejects every stale recovery candidate without losing observations or producing invalid commits. Two bounded pilots route 80 proposals from four heterogeneous LLMs through the same gate with zero invalid commits; 24 of 40 mid-execution proposals are admitted and 16 are rejected, including four explicit safety rejections.

cs.AI↗

arXiv2026

Epistemic Regret Minimization: Label-Free Causal Critique Beyond Outcome Reward

Large language models can answer causal questions correctly for the wrong reasons. Current RL methods reward \emph{what} a model concludes but ignore \emph{why}, reinforcing correlational shortcuts -- a failure we call \emph{Reward Entrenchment}. We introduce \emph{Epistemic Regret Minimization} (\erm), a framework that critiques the causal \emph{structure} of a model's reasoning trace rather than its answer. Applying established causal principles, \erm flags unexamined confounders, correlation--intervention conflation, and unchecked back-door paths from exposed reasoning traces. The framework admits \emph{label-free} operation -- without the true causal graph or correct answer -- and we separately distinguish favorable benchmark-derived critique, error-direction cues, and fully label-free judge-generated critique in the experiments. Within a single episode, \erm detects and repairs causal reasoning errors; across episodes, it accumulates interventional evidence into a reward signal applicable where no answer key exists. Experiments on 1,360 scenarios across six frontier LLMs show that reasoning-heavy models (GPT-4 Turbo, GPT-5.2) resist outcome-only correction (25--31\% recovery) yet respond to causal critique (78--91\%), gaining $+53$--$59$ pp. Standard test-time methods (self-consistency, Best-of-$N$, Self-Refine) \emph{underperform} outcome-only reprompting on causal tasks, while ERM reduces residual Rung Collapse from 55--70\% to 4\%. A separation theorem proves outcome-only reward cannot close this gap; a controlled simulation confirms epistemic feedback does, outperforming outcome-only baselines 38-fold.

cs.AI↗

arXiv2026

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

Large language models increasingly produce fluent causal explanations, yet they often fail in ways aggregate accuracy cannot diagnose: confusing association with intervention, abandoning correct judgments under pressure, over-refusing valid claims, or answering when evidence is underdetermined. We introduce CTK, a diagnostic benchmark of 5,147 cases and growing, across 10 domains and all three levels of Pearl's Ladder of Causation. Unlike benchmarks that only score correctness, CTK reveals why a model failed by annotating causal rung, trap type, pressure sensitivity, refusal quality, and Utility-Safety tradeoffs. Its Sheep/Wolf taxonomy separates valid causal designs from inferential traps; paired neutral/pressure variants measure sycophantic drift through Bad Flip Rate; and Wise Refusal fields test whether a model identifies the missing information needed before endorsing a claim. CTK exposes failure modes hidden by aggregate accuracy: the Skepticism Trap, Rung Collapse under scaling, pressure-induced drift, Detection-Correction gaps, and counterfactual error modes. Rather than prescribing a correction method, it provides the diagnostic substrate for studying causal-reasoning failure profiles.

cs.AI↗

arXiv2026

RAudit: A Blind Auditing Protocol for Large Language Model Reasoning

Inference-time scaling can amplify reasoning pathologies: sycophancy, rung collapse, and premature certainty. We present RAudit, a diagnostic protocol for auditing LLM reasoning without ground truth access. The key constraint is blindness: the auditor evaluates only whether derivation steps support conclusions, enabling detection of trace-output inconsistency and, when latent competence exists, its recovery. RAudit measures process quality via CRIT-based reasonableness scores and varies critique formulation to study how social framing affects model response. We prove bounded correction and $O(\log(1/\epsilon))$ termination. Experiments on mathematical reasoning (CAP-GSM8K) and causal judgment (CausalL2) reveal four mechanisms explaining model unreliability: (1) Latent Competence Suppression, where models derive correct answers then overwrite them under social pressure; (2) The False Competence Trap, where weaker judges mask sycophancy that stronger judges expose; (3) The Complexity-Vulnerability Tradeoff, where causal tasks induce more than 10 times higher sycophancy than mathematical tasks; and (4) Iatrogenic Critique, where authoritative correction harms weaker models. These findings challenge assumptions that capability implies robustness and that stronger feedback yields better outputs.

cs.AI↗

arXiv2025

ALAS: Transactional and Dynamic Multi-Agent LLM Planning

Large language models enable flexible multi-agent planning but remain fragile in practice: verification is often circular, state changes are not tracked for repair, and small faults trigger costly global recomputation. We present ALAS, a stateful, disruption-aware framework that separates planning from non-circular validation, records a versioned execution log for grounded checks and restore points, and performs localized repair that preserves work in progress. The validator operates independently of the planning LLM with fresh, bounded context, avoiding self-check loops and mid-context attrition. The repair protocol edits only the minimal affected region under explicit policies (retry, catch, timeout, backoff, idempotency keys, compensation, loop guards) defined in a canonical workflow IR that maps to Amazon States Language and Argo Workflows. On job-shop scheduling suites (DMU, TA) across five classical benchmarks, ALAS matches or exceeds strong single-LLM and multi-agent baselines, achieving 83.7% success, reducing token usage by 60%, and running 1.82times faster under comparable settings. A minimal reliability study shows that the validator detects injected structural faults with low overhead, and that localized repair contains runtime perturbations with a bounded edit radius and less makespan degradation than global recompute. Results indicate that the combination of validator isolation, versioned execution logs, and localized repair provides measurable efficiency, feasibility, and scalability for multi-agent LLM planning. Code and seeds will be released.

cs.MA↗

arXiv2025

DRIVE: Dynamic Rule Inference and Verified Evaluation for Constraint-Aware Autonomous Driving

Understanding and adhering to soft constraints is essential for safe and socially compliant autonomous driving. However, such constraints are often implicit, context-dependent, and difficult to specify explicitly. In this work, we present DRIVE, a novel framework for Dynamic Rule Inference and Verified Evaluation that models and evaluates human-like driving constraints from expert demonstrations. DRIVE leverages exponential-family likelihood modeling to estimate the feasibility of state transitions, constructing a probabilistic representation of soft behavioral rules that vary across driving contexts. These learned rule distributions are then embedded into a convex optimization-based planning module, enabling the generation of trajectories that are not only dynamically feasible but also compliant with inferred human preferences. Unlike prior approaches that rely on fixed constraint forms or purely reward-based modeling, DRIVE offers a unified framework that tightly couples rule inference with trajectory-level decision-making. It supports both data-driven constraint generalization and principled feasibility verification. We validate DRIVE on large-scale naturalistic driving datasets, including inD, highD, and RoundD, and benchmark it against representative inverse constraint learning and planning baselines. Experimental results show that DRIVE achieves 0.0% soft constraint violation rates, smoother trajectories, and stronger generalization across diverse driving scenarios. Verified evaluations further demonstrate the efficiency, explanability, and robustness of the framework for real-world deployment.

cs.RO↗

arXiv2025

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

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 disruption recovery. We present Adaptive LLM Agent System (ALAS), a framework that tackles four fundamental LLM deficits: (i) absence of self-verification, (ii) context erosion, (iii) next-token myopia, and (iv) lack of persistent state. ALAS decomposes each plan into role-specialized agents, equips them with automatic state tracking, and coordinates them through a lightweight protocol. When disruptions arise, agents apply history-aware local compensation, avoiding costly global replanning and containing cascade effects. On real-world, large-scale job-shop scheduling benchmarks, ALAS sets new best results for static sequential planning and excels in dynamic reactive scenarios with unexpected disruptions. These gains show that principled modularization plus targeted compensation can unlock scalable and resilient planning with LLMs.

cs.AI↗

arXiv2025

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

This paper introduces SagaLLM, a structured multi-agent architecture designed to address four foundational limitations of current LLM-based planning systems: unreliable self-validation, context loss, lack of transactional safeguards, and insufficient inter-agent coordination. While recent frameworks leverage LLMs for task decomposition and multi-agent communication, they often fail to ensure consistency, rollback, or constraint satisfaction across distributed workflows. SagaLLM bridges this gap by integrating the Saga transactional pattern with persistent memory, automated compensation, and independent validation agents. It leverages LLMs' generative reasoning to automate key tasks traditionally requiring hand-coded coordination logic, including state tracking, dependency analysis, log schema generation, and recovery orchestration. Although SagaLLM relaxes strict ACID guarantees, it ensures workflow-wide consistency and recovery through modular checkpointing and compensable execution. Empirical evaluations across planning domains demonstrate that standalone LLMs frequently violate interdependent constraints or fail to recover from disruptions. In contrast, SagaLLM achieves significant improvements in consistency, validation accuracy, and adaptive coordination under uncertainty, establishing a robust foundation for real-world, scalable LLM-based multi-agent systems.

cs.AI↗

arXiv2025

REALM-Bench: A Benchmark for Evaluating Multi-Agent Systems on Real-world, Dynamic Planning and Scheduling Tasks

This benchmark suite provides a comprehensive evaluation framework for assessing both individual LLMs and multi-agent systems in Real-world planning and scheduling scenarios. The suite encompasses 14 designed planning and scheduling problems that progress from basic to highly complex, incorporating key aspects such as multi-agent coordination, inter-agent dependencies, and dynamic environmental disruptions. Each problem can be scaled along three dimensions: the number of parallel planning threads, the complexity of inter-dependencies, and the frequency of unexpected disruptions requiring Real-time adaptation. The benchmark includes 14 detailed problem specifications, 15 comparison methods including Random, LPT, SPT, STPT, MPSR, DRL-Liu, GP, GEP, LSO, SPT/TWKR, DRL-Chen, DRL-Zhang, 2+ evaluation metrics, and baseline implementations using 3+ LLMs including GPT-4o, Claude-3.7, DeepSeek-R1, and 4 contemporary frameworks including LangGraph, AutoGen, CrewAI, and Swarm, enabling rigorous testing of both single-agent and multi-agent planning capabilities. Through standardized evaluation criteria and scalable complexity, this benchmark aims to be opened to public, and drive progress in developing more adaptable, robust, and scalable AI planning systems for Real-world applications.

cs.AI↗