arXiv subjects

Mayank Anand

Publications and source records attributed to Mayank Anand.

5 recordsLinked to original sources

arXiv2026

MEMOIR: A Training-Free Memory Lifecycle for Long-Horizon LLM Agents

Long-horizon LLM agents require memory systems that preserve useful information across sessions and retrieve it when needed. Existing systems treat these as separate problems: memories are written prospectively with static importance scores that are never revised after use. This creates two coupled failure modes: consolidation can silently destroy evidence that future queries require, while retrieval continues to favor stale memories. We propose MEMOIR (Memory Evidence via Merge-certified, Online Importance Revision), a training-free memory lifecycle that unifies judge-gated consolidation with retrospective attribution. Before compressing memory, screening gates test whether answer-relevant evidence is preserved. After each query, attribution estimates which retrieved memories supported the answer and updates their retrieval priority. A UCB-style exploration bonus additionally encourages retrieval of under-exposed memories, reducing the risk that frequently retrieved memories crowd out useful but less-seen evidence. On 1,905 deduplicated LoCoMo QA pairs, the full retrieval stack improves evidence recall@5 by 11.92 percentage points over bare cosine, with confidence-gated feedback adding 1.50 points overall without reference answers or reranker training; a deployment-unavailable oracle adds 1.84 points overall and 8.05 points on multi-hop. Judge-gated merge changes the recall of text-based evidence from 58.82% to 59.08%, reduces the active store by 1.42%, and incurs 0 observed losses in 100 independently audited merges, with a one-sided 95% upper loss-rate bound of 2.95%. Together, these results outline a practical deployment path: no additional LLM call on the online write path, with merge screening confined to periodic offline consolidation. The lifecycle reduces to one principle: attribute usefulness after use, and screen for preservation before compression.

cs.IR↗

arXiv2026

Viable Pool Sizing for On-Chain FX Liquidity: Amplification, Capital, and Resilience

Financial institutions deploying on-chain FX liquidity face a joint design problem: how much capital to commit, and how to configure the pool, to remain both competitive on trading costs and profitable as a liquidity provider? The StableSwap mechanism (Egorov, 2020) interpolates between constant-product (CPMM) and constant-sum (CSMM) market makers (Port and Tiruviluamala, 2022) via an amplification factor A, but neither extreme suits institutional FX: CPMM pools require excessive capital and generate high impermanent loss; CSMM pools are capital-efficient near the peg but drain rapidly under adversarial flow. Using a Merton jump-diffusion price process (Merton, 1976) and the loss-versus-rebalancing (LVR) framework (Milionis et al., 2022), we map the joint (A, TVL) space to identify configurations that satisfy all three institutional requirements: competitive slippage, positive return, and shock resilience. Minimum viable pool size scales approximately as TVL/Q = 1000/A; ROC at that minimum is thin (about 0.054% per horizon) and independent of A; low-A pools (A <= 10) suffer slippage exceeding 200 bps under a 10x shock, while high-A pools (A >= 500) suffer reserve drain up to 60%, establishing both a capital floor and a practical amplification ceiling.

cs.CE↗

arXiv2026

HARPO: Hierarchical Agentic Reasoning for User-Aligned Conversational Recommendation

Conversational recommender systems (CRSs) operate under incremental preference revelation, requiring recommendation decisions under uncertainty. While recent LLM-based approaches achieve strong performance on proxy metrics such as Recall@K and BLEU, they often fail to deliver high-quality, user-aligned recommendations in practice, as they optimize intermediate objectives like retrieval accuracy or fluent generation rather than recommendation quality itself. We propose HARPO (Hierarchical Agentic Reasoning with Preference Optimization), an agentic framework that reframes conversational recommendation as a structured decision-making process optimized for multi-dimensional recommendation quality. HARPO integrates (i) hierarchical preference learning that decomposes recommendation quality into interpretable dimensions (relevance, diversity, satisfaction, and engagement) with context-dependent weighting; (ii) deliberative tree-search reasoning guided by a learned value network evaluating candidate paths on predicted quality; and (iii) domain-agnostic reasoning abstractions through Virtual Tool Operations and multi-agent refinement. We evaluate HARPO on ReDial, INSPIRED, and MUSE, demonstrating consistent improvements over strong baselines on recommendation-centric metrics while maintaining competitive response quality.

cs.IR↗

arXiv2026

QueST: Persistent Queries as Semantic Monitors for Drift Suppression in Long-Horizon Tracking

Tracking points in videos is typically formulated as frame-to-frame correspondence, where each point is matched locally to the next frame. While this works over short horizons, errors accumulate under articulation, occlusion, and viewpoint change, leading to silent semantic drift that existing trackers cannot detect or correct. In this work, we revisit long-horizon tracking from a monitoring perspective and introduce QueST, a monitoring-by-design framework that treats interaction-relevant entities as persistent semantic queries rather than transient point tracks. Instead of local propagation, each query attends globally over spatio-temporal video features at every time-step, providing a stable semantic anchor across time. We further constrain query trajectories with lightweight 3D physical grounding, using geometric plausibility to suppress unbounded drift under occlusion. We evaluate QueST on long-horizon articulated sequences from PartNet-Mobility in SAPIEN and compare against RAFT-3D, CoTracker, and TAP-Net. QueST substantially reduces terminal drift achieving a 67.7% Absolute Point Error (APE) improvement over TAP-Net while better preserving identity over extended horizons. Our results show that embedding semantic monitoring directly into perception enables more reliable long-horizon tracking under distribution shift.

cs.CV↗

arXiv2025

UltrasODM: A Dual Stream Optical Flow Mamba Network for 3D Freehand Ultrasound Reconstruction

Clinical ultrasound acquisition is highly operator-dependent, where rapid probe motion and brightness fluctuations often lead to reconstruction errors that reduce trust and clinical utility. We present UltrasODM, a dual-stream framework that assists sonographers during acquisition through calibrated per-frame uncertainty, saliency-based diagnostics, and actionable prompts. UltrasODM integrates (i) a contrastive ranking module that groups frames by motion similarity, (ii) an optical-flow stream fused with Dual-Mamba temporal modules for robust 6-DoF pose estimation, and (iii) a Human-in-the-Loop (HITL) layer combining Bayesian uncertainty, clinician-calibrated thresholds, and saliency maps highlighting regions of low confidence. When uncertainty exceeds the threshold, the system issues unobtrusive alerts suggesting corrective actions such as re-scanning highlighted regions or slowing the sweep. Evaluated on a clinical freehand ultrasound dataset, UltrasODM reduces drift by 15.2%, distance error by 12.1%, and Hausdorff distance by 10.1% relative to UltrasOM, while producing per-frame uncertainty and saliency outputs. By emphasizing transparency and clinician feedback, UltrasODM improves reconstruction reliability and supports safer, more trustworthy clinical workflows. Our code is publicly available at https://github.com/AnandMayank/UltrasODM.

cs.CV↗