Searcharxiv⌕ Search

arXiv subjects

Edward Y. Chang

Publications and source records attributed to Edward Y. Chang.

At least 19 recordsLinked to original sources
arXiv2026

EVINCE: Optimizing Multi-LLM Dialogues Using Conditional Statistics and Information Theory

EVINCE (Entropy and Variation IN Conditional Exchanges) is a novel framework for optimizing multi-LLM dialogues using conditional statistics and information theory. It addresses limitations in multi-agent debate (MAS) frameworks, where multiple LLMs chat without behavior modulation or mutual information quality assessment. Using dual entropy optimization to balance perspective diversity and prior knowledge, EVINCE provides quantitative tools to dynamically regulate LLM linguistic behaviors. When mutual information is low and both cross-entropy and Wasserstein distance are high, EVINCE promotes contentious dialogues to expose diverse perspectives and uncover inconsistencies. Conversely, as cross-entropy decreases and mutual information stabilizes, it transitions discussions into a conciliatory phase, encouraging compromise and acknowledgment of valid points. Using information-theoretic metrics and optimizing mutual information, EVINCE emerges as a structured and highly effective framework for multi-LLM collaboration.

cs.AI↗
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

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

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), to our knowledge the first commitment-level consistency contract for world models. TRW treats predicted state as a materialized view and a physical commitment as a read whose authorization can expire. Typed, calibrated claims specify consequence-conditioned freshness and priced verification. Adaptive refresh generalizes dual-Kalman synchronization to consult the world when evidence could change a decision; dependency-scoped SagaLLM compensation repairs reversible commitments invalidated after authorization. Under an event-aligned risk oracle and recovery-liveness assumptions, we prove that synchronization and compensation are insufficient alone, whereas their composition gives a conditional consistency guarantee. Otherwise, the argument yields an auditable decomposition of violations into named debts. We implement TRW in Flood-SAR, a search-and-rescue simulator over real geography, and test six preregistered questions at frozen operating points on held-out seeds. Adaptive refresh reduces stale execution but does not dominate fixed refresh on cost, coverage, or rescue outcomes. Localized repair reduces repair work by 9.56 units per mission and restoration latency by 80.7 seconds relative to global recovery; the observed residual-violation difference is zero without establishing equivalence. Detection coverage is 0.83-0.89, and 10 of 97 invoked restorations are incomplete by mission end. The campaign treats empirical slack as sensitivity inputs rather than discharging the theorem's assumptions or providing a simultaneous population certificate. Exact replay reconstructs a disputed dispatch. TRW thus makes a world model an auditable predictive interface rather than a self-validating source of truth.

cs.AI↗
arXiv2026

Trivium: Temporal Regret as a First-Class Objective for Causal-Memory Controllers

Many agentic systems and LLM pipelines correct mistakes by optimizing outcome reward. This addresses only the what of failure; the why and when may go unlogged, allowing the same error to recur across episodes. We propose long-horizon temporal regret alongside outcome regret and epistemic regret. These are diagnostic quantities, not standard comparator-based online-learning regrets. Temporal regret captures how long an unresolved or incorrect causal model is tolerated; epistemic regret captures posterior error over that model. Over a stream of E episodes, we prove three conditional results under explicit probing, persistence, and detectability assumptions. First, under observationally equivalent confounding, outcome-only learning cannot separate causal from spurious structure, so miscalibration can persist after outcome regret reaches zero. Second, with a persistent causal log and budgeted probes, total probe complexity is logarithmic in E, inducing O(log E) delayed-identification temporal regret. The implemented clipped soft score adds a linear numerical floor, so this logarithmic claim applies only to identification delay. Third, under K detectable change-points, the rate extends to O(K log E). We instantiate Trivium and state five falsifiable predictions. On CausalBench-Seq, a hard structural readout records 7.8+-2.9 misidentified episodes per seed over 500 episodes and 20 seeds, with zero observed stationary errors, while outcome-only controllers remain misidentified throughout. Audit ablations show that continued posterior updating, not detector reopening or local repair, drives posterior recovery; local repair instead reduces committed-graph dispatch exposure. The prior logarithmic-envelope verdict based on a clipped soft score is withdrawn. A pilot real-LLM stream provides external evidence. Self-learning here means revising an external causal model, not retraining LLM weights.

cs.AI↗
arXiv2026

TRACE: An Operational Reasoning Schema for Auditable Agentic Commitments

This paper defines TRACE (Typed Reasoning And Commitment Evidence): a typed, versioned schema for recording reasoning traces, a reference procedure for writing records against it, and one operating discipline, no durable state change without a record. The paper argues in three layers that reasoning is not in the language model: the autoregressive mechanism natively computes association; chain-of-thought and reinforcement learning inherit its limits; and the formal constructs of reasoning theory, from Socratic procedure to Pearl's ladder, are absent as machinery. The schema answers the absence with fields and tests: the TraceRecord and its causal specialization, an eight-stage reference writer, a gate-first measurement regime, the TRACE-Bench protocol, and the consumers, memory admission, plan gating, temporal regret, and verdict reuse, whose more auditable decisions are the measure of the record. A record-consumer contract states what a record guarantees and what a consumer must honor in return, making the schema an operational interface rather than a passive document. Two worked examples run in the main text: a music-lessons argument traced from sentence to typed verdict, separating association, intervention, and prescription; and a flood search-and-rescue vignette in which a predictive world model reports confident plan success that its own support and out-of-distribution scores contradict, so the record defers the commitment, requests a bounded observation, revises append-only, and clears a different branch. The vignette is illustrative, not empirical; closed-loop evaluation is left to future work, so the contribution is the schema and its contract, not a performance claim. Appendices carry the full schema, writer algorithms and cost model, clinical and policy illustrations, the benchmark protocol, convergence metrics, and usage scenarios.

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

Architectural Wisdom: A Framework for Governing Optimization in AI Systems

Modern AI systems exhibit structural failures that capability scaling alone does not reliably fix: they optimize under-specified objectives with no architectural mechanism to question whether the objective should be optimized at all. Engagement maximization can amplify harmful pathways; tool-using agents can commit irreversible actions; preference-trained language models can become sycophantic. We argue that this failure is a wisdom problem, not an intelligence problem. We use "wisdom" in a deliberately architectural sense, not as a claim about virtue, consciousness, or moral omniscience. Intelligence accepts a goal and optimizes within it; wisdom interrogates whether the goal should be optimized at all. The two are separable architectural properties. We propose architectural wisdom as a corrigible objective-governance layer above the optimization substrate. The layer makes three structural commitments explicit and nondegenerate before any action: temporal horizon, relational boundary, and irreversibility. It is realized by four components (Structural Utility Transform, Moral Admissibility Interface, Arbitration and Escalation Controller, Value Revision Channel) that compute a six-coordinate wisdom tuple over horizon, relational coverage, irreversibility, admissibility, value revision, and auditability. We motivate the architecture by eight cases drawn from contemporary AI failures, secular wisdom traditions, and hard ethical situations, and defend the distinction against the intelligence-completeness thesis using goal-questioning over goal-taking, Bostrom's orthogonality, structural separation in our exemplar cases, and persistent failure modes despite capability scaling. The framework is the conceptual contract for a larger architecture whose formal specifications and empirical validation are developed in subsequent work.

cs.AI↗
arXiv2026

AGI Requires a Coordination Layer on Top of Pattern Repositories

In this paper we argue that influential critiques dismissing Large Language Models (LLMs) as a dead end for AGI misidentify the bottleneck: they confuse the ocean with the net. Pattern repositories are the necessary System-1 substrate; the missing component is a System-2 coordination layer that recruits relevant patterns, verifies their use, preserves state, and governs convergence. We separate two uses of control that are often conflated. Semantic anchoring, formalized by UCCT (Unified Contextual Control Theory), binds labels and task intent to learned pattern regions through a phase transition governed by effective support (rho_d), representational mismatch (d_r), and an adaptive anchoring budget (gamma log k). Trace-answer verification, implemented by Recursive Causal Audit (RCA), tests whether a final causal judgment is warranted by its own reasoning trace under pressure. We translate these ideas into MACI, a multi-agent coordination stack that integrates diversity and control via baiting (PID-modulated debate), filtering (Socratic and causal audit), and persistence (transactional memory). Empirical validation on causal judgment and the sycophancy-paranoia trade-off demonstrates that static prompting fails where adaptive control succeeds. By reframing common objections as testable coordination failures, we argue that the path to AGI runs through LLMs, not around them. Capability is not coordination.

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

Exploring Collatz Dynamics with Human-LLM Collaboration

We present a comprehensive structural analysis of the Collatz conjecture through ~1014 computational experiments yielding 630 formal results. By systematically deploying 29 distinct mathematical paradigms--including transfer operator spectral theory, S-unit equations, p-adic interpolation, martingale methods, modular sieving, formal language theory, cascade algebra, discrete logarithm obstruction, and Diophantine approximation--we establish a Paradigm Exhaustion Theorem: every known framework for promoting distributional convergence ("almost all orbits descend") to pointwise convergence ("all orbits descend") encounters an irreducible structural obstruction when applied to the Syracuse map. On the unconditional side, we prove: (i) the Syracuse transfer operator has a uniform spectral gap for all M, implying equidistribution modulo any power of 2; (ii) any nontrivial cycle of length L satisfies D > 2^F for all L >= 3, giving ord_D(2) > F and F+1 distinct residues mod D; (iii) divergent starting points have natural density 0 and Hausdorff dimension ~0.68; (iv) the formal language of divergent-compatible v-sequences is not context-free; (v) cylinder-averaged density-1 convergence is proved unconditionally via spectral contraction on the invariant core I_2; (vi) a discrete logarithm triple filter achieves 100% cycle blockage for all L tested. We identify the Distributional-to-Pointwise Gap as the irreducible core and prove it equivalent to the divergence component. The modular sieve is permanently nonempty via the Mersenne Bypass. The present work is not a proof of the Collatz conjecture; it characterizes why the conjecture resists proof. The 29-paradigm exhaustion constitutes the most comprehensive structural survey of Collatz attack surfaces to date. Produced through human-LLM collaboration; see Section 12.

math.DS↗
arXiv2026

Diagnosing and Mitigating Sycophancy and Skepticism in LLM Causal Judgment

Large language models increasingly fail in a way that scalar accuracy cannot diagnose: they produce a sound reasoning trace and then abandon it under social pressure or an authoritative hint. We argue that this is a control failure, not a knowledge failure, and that it requires an evaluation surface richer than a single accuracy number. We introduce CAUSALT3, a 454 instance expert curated benchmark for causal reasoning across all three rungs of Pearl's ladder, and a three axis evaluation that decomposes performance into Utility (sensitivity to valid causal claims), Safety (specificity against invalid ones), and Wise Refusal (calibrated abstention on genuinely underdetermined items). On this surface we document three reproducible pathologies: a Skepticism Trap at L1 where capable models over refuse sound links, a Sycophancy Trap at L2 where confident user pressure flips correct answers, and a Scaling Paradox at L3 where a frontier model underperforms an older one on counterfactual Safety by 55 points. To mitigate these failures without retraining, we propose Regulated Causal Anchoring (RCA), an inference time process verifier that audits trace output consistency under a PID style feedback loop and abstains rather than ratifying a detected mismatch. Across CAUSALT3 and a supporting CAP-GSM8K stress test, RCA reduces sycophantic acceptance to near zero while preserving valid hint acceptance, recasting trustworthy reasoning as a question of inference time control rather than scale.

cs.AI↗
arXiv2026

A Structural Reduction of the Collatz Conjecture to One-Bit Orbit Mixing

We reduce the Collatz conjecture to a fixed-modulus, one-bit orbit-mixing problem. Working with the compressed odd-to-odd Collatz map, we prove exact low-depth decomposition formulas at depths K = 3, 4, 5, reducing block-discrepancy terms to explicit run statistics. We then prove a Map Balance Theorem: among the 2^(K-3), 1 burst residues modulo 2^K that initiate gaps, the counts mapping to gap starts congruent to 3 versus congruent to 7 (mod 8) differ by exactly 1 for every K >= 5. Thus all residual bias is orbit-level, not map-level. For the dominant n congruent to 1 (mod 8) class, the gap outcome depends on a single binary variable, bit 4 of the orbit value at burst-ending times, reducing the conjecture to whether every orbit visits two residue classes modulo 32 with sufficient balance along a sparse subsequence.

math.DS↗
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 $O(\log(1/ε))$ 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↗
arXiv2026

Internal Reasoning vs. External Control: A Thermodynamic Analysis of Sycophancy in Large Language Models

Large Language Models exhibit sycophancy: prioritizing agreeableness over correctness. Current remedies evaluate reasoning outcomes: RLHF rewards correct answers, self-correction critiques outputs. All require ground truth, which is often unavailable at inference time and vulnerable to the same biases. We explore evaluating the reasoning process instead. Regulated Causal Anchoring (RCA) verifies whether outputs follow from their reasoning traces, without requiring ground truth. Sycophancy manifests as trace-output inconsistency: models derive one answer but output another to please users. RCA detects this inconsistency, achieving 0.0% sycophancy while accepting 88% of valid hints. We identify two failures invisible to outcome evaluation: Inverse Scaling (frontier models sycophant more because rationalization requires capability) and the Final Output Gap (correct reasoning precedes sycophantic output). Traditional self-correction reduces these failures to 7-9% but cannot eliminate them because the model critiques itself with the same biases. RCA's process evaluation operates at inference time, requires no ground truth, and uses an independent judge that breaks the self-reinforcing bias loop: three properties that outcome evaluation lacks.

cs.CL↗
arXiv2025

The Unified Cognitive Consciousness Theory for Language Models: Anchoring Semantics, Thresholds of Activation, and Emergent Reasoning

We propose semantic anchoring, a unified account of how large language models turn pretrained capacity into goal-directed behavior: external structure (in-context examples, retrieval, or light tuning) binds the model's latent patterns to desired targets. Unified Contextual Control Theory (UCCT) formalizes this via anchoring strength $S = ρ_d - d_r - \log k$, where $ρ_d$ measures target cohesion in representation space, $d_r$ measures mismatch from prior knowledge, and $k$ is the anchor budget. UCCT predicts threshold-like performance flips and strictly generalizes in-context learning, reading retrieval and fine-tuning as anchoring variants. Three controlled studies provide evidence. Experiment 1 demonstrates cross-domain anchoring rebinding strong priors in text and vision. Experiment 2 varies representational familiarity via numeral bases (base-10/8/9) at fixed complexity, yielding ordered thresholds and transfer patterns tracking $ρ_d$, $d_r$, and $S$. Experiment 3 establishes a geometry-to-behavior correlate: layer-wise peak anchoring and trajectory area predict few-shot thresholds $θ_{50}$. UCCT offers testable theory and practical metrics for optimizing prompts, retrieval, and tuning.

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

Inverse-Free Wilson Loops for Transformers: A Practical Diagnostic for Invariance and Order Sensitivity

Large language models can change answers under harmless edits that matter in practice: RAG outputs flip when passages are reordered, fine-tuning erodes invariances learned at pretraining, debate or chain-of-thought prompts take path-dependent routes, and compiler fusion or reordering perturbs logits near decision boundaries. These failures violate intended invariances, break continuous integration, and force teams to trade safety for speed. The effects are small yet distributed across layers and positions, sensitive to context length and evaluation order, and costly to repair with retraining or formal verification. We present WILSON, a minimal post-hoc diagnostic suite that converts simple loop and reordering checks on internal representations into system signals. WILSON combines an inverse-free curvature map over positions and layers, computed with JVPs and Hutchinson probes, with activation-level commutators that flag reorder risk. Signals are cheap to compute, model-agnostic for standard Transformers, and exported as thresholds and CSV artifacts for orchestrators. This enables concrete actions: guard RAG against order effects, catch fine-tuning regressions, stabilize debate pathways and long multi-turn contexts, and gate fusions or reorders in deployment. In short, WILSON helps anticipate failures and approve safe optimizations so reliability and throughput can improve together without changing model architecture or training.

cs.LG↗
arXiv2025

Multi-Agent Collaborative Intelligence: Dual-Dial Control for Reliable LLM Reasoning

Multi-agent debate often wastes compute by using a fixed adversarial stance, aggregating without deliberation, or stopping on heuristics. We introduce MACI, an active controller with two independent dials that decouple information from behavior: an information dial that gates evidence by quality, and a behavior dial that schedules contentiousness from exploration to consolidation. A moderator tracks disagreement, overlap, evidence quality, and argument quality, and halts when gains plateau. We provide theory-lite guarantees for nonincreasing dispersion and provable termination, with a budget-feasible scheduler. Across clinical diagnosis and news-bias tasks, MACI improves accuracy and calibration while reducing tokens, and converts residual uncertainty into precision RAG plans that specify what to retrieve next. We use a cross-family LLM judge (CRIT) as a conservative soft weight and stop signal, validated for order invariance and judge-swap stability; stability depends on using high-capability judges. MACI turns debate into a budget-aware, measurable, and provably terminating controller.

cs.AI↗