Experiments show that AP-REASONER outperforms baseline subsamplers on structure-sensitive downstream tasks and enables controllable recovery of alternative protein conformations, highlighting the value of modeling MSA subsampling as a controllable optimization problem, where factor-graph reasoning offers an effective alternative to heuristic selection.
Abstract
Multiple Sequence Alignments (MSAs) provide protein language models with explicit evolutionary context, but their large depth makes subsampling unavoidable under limited token budgets. Existing strategies, including random selection, identity-based filtering, and diversity-driven sampling, are effective heuristics, yet provide limited control over the evolutionary signals retained in the subset. In this work, we recast MSA subsampling as an explicit optimization problem, where key evolutionary measures, including query identity and diversity, are treated as controllable objectives. Building on this view, we introduce AP-REASONER, an Affinity-Propagation-based factor-graph approach. With evolution-aware unary factors, exemplar-consistency factors, and two control knobs, AP-REASONER performs factor-graph reasoning through message passing to infer a fixed-budget MSA subset. Experiments on long-range contact prediction and conformational ensemble prediction show that AP-REASONER outperforms baseline subsamplers on structure-sensitive downstream tasks and enables controllable recovery of alternative protein conformations. These results highlight the value of modeling MSA subsampling as a controllable optimization problem, where factor-graph reasoning offers an effective alternative to heuristic selection.
OptGraph is the first optimization agentic workflow that introduces graph retrieval-augmented generation (GraphRAG) and first constructs reusable experience as a typed graph, capturing the relationships among modeling patterns, problem formalization, implementation details, and error corrections.
Xianchao Xiu, Jianhao Li, Huangyue Chen et al.· 1 citation
Large Language Models (LLMs) explore problems through chain-of-thought, but this exploration is buried in unstructured prose. On high-stakes tasks, users cannot tell which steps are well-supported, which alternatives were seriously considered, or how the final conclusion compares to those the model discarded. We propose a framework that ensembles the reasoning structure, not just the answers, of multiple LLMs by weighted merging of Directed Acyclic Graphs (DAGs) extracted from reasoning chains. We weight each step by how many traces independently attest to it, to return"Consensus Reasoning". Across six benchmarks spanning statutory interpretation, graduate-level science, narrative multi-hop reasoning, and first-order logic, our ensemble outperforms a matched-budget majority-vote baseline, with a maximum accuracy gain of 3.1% on MuSR-MM (narrative multi-hop reasoning). On a single model, the framework matches or exceeds self-consistency at the same trace budget while additionally exposing an inspectable consensus reasoning graph. Ensemble weights correlate with LLM-judge rankings of reasoning quality at Spearman $\rho = 0.30$-$0.51$, and consensus subgraphs are preferred over alternatives leading to the majority-vote answer in 54.4-65.4% of head-to-head comparisons across five of six datasets. We observe that our framework can also be used to analyze diverse reasoning perspectives for a problem.
Amruta Parulekar, Jinu Lee, Dilek Z. Hakkani-Tür et al.· 0 citations
Dynamic programming (DP) yields exact quadratic-time (O(NM)) pairwise sequence alignments. Static banding heuristics (O(NW)) fail catastrophically on low-identity (< 30%), asymmetric insertions/deletions (indels), or extreme length ratios, dropping core-block Sum-of-Pairs (SP) score recovery to 20%– 50%. Conversely, recent protein language model (PLM) aligners evaluate all N × M cells without search grid constraints. To bridge this gap, we introduce Adaptive-Banding Needleman–Wunsch (AB-NW), leveraging PLM contextual representations to construct a confidence-adaptive DP corridor prior to fine-resolution DP while keeping downstream scoring unmodified. AB-NW downsamples residue embeddings, computes a coarse alignment, and sets per-row corridor bounds via normalized confidence metrics. Evaluated via JIT-compiled buffers, this reduces time complexity to and space to O(NWmax) . Benchmarked across three PLM backbones (ESM2-8M, ESM2-35M, ProtBERT) across nine structural challenge categories, AB-NW recovers > 98.9% of exact unconstrained alignment scores and core-block SP accuracy across static banding failure modes (Twilight Zone, Asymmetric Indels, Extreme Aspect Ratios) while eliminating 55.3%–78.8% of active DP cells. On large protein matrices (N, M ≥ 3, 700), AB-NW eliminates 87.6%– 91.7% of cells, achieving speedups of 9.79×–13.30× (pure DP) and 1.73×– 2.94× (end-to-end), reaching up to 18.12× on unbiased controls (p < 0.05 to p < 10−15), making AB-NW practical for large-scale, high-throughput sequence alignment pipelines.
Large neighborhood search normally selects a random subset of decision variables for iterative optimization. To efficiently solve various problems, researchers tend to design variable selection strategies that take into account structural features across different domains. In this paper, we build an automatic pipeline that is problem-agnostic to all problems in the MiniZinc format. By prompting an LLM with our semantic guidelines, we guide the LLM to produce a graph generator that maps any instance of a problem type to a uniform weighted graph, where nodes represent decision variables and edges represent constraint relationships. These problem-agnostic graphs guide our structure-based local improvement (SLIM) framework for variable selection. Meanwhile, the weighted graph enables all problem instances to share the same generic graph representation, from which the same graph features can be extracted and used for configuration selection. We evaluated our pipeline on instances across 20 MiniZinc competition problems, finding that algorithm selection achieves a 39.6% average problem-weighted win rate against a one-shot Gurobi baseline, more than doubling the best single configuration (19.3%). A post-hoc configuration and a feature ablation indicate a headroom of up to 44.0%, demonstrating that LLM-based semantic generation enables effective automated structure and feature extraction for constraint optimization.
Hai Xia, Vaidyanathan Peruvemba Ramaswamy, Stefan Szeider· 0 citations
This work introduces QUORUM (QUality-Optimized Routing Using Multiple annotators), a budget-aware routing framework that dynamically assigns each instance to human or LLM annotators under a fixed annotation budget and supports multiple annotations per instance, combining them through agreement-based rewards to improve reliability.
Antonio Purificato, Maria Sofia Bucarelli, Andrea Bacciu et al.· 0 citations
Evaluated across nine SMT logics, SMT-Select consistently outperforms existing selectors and SMT-COMP winning solvers and closes at least 30% of the performance gap between the competition winner and the virtual best solver (VBS).
Zhengyang Lu, Paul Sarnighausen-Cahn, Jiahao Chen et al.· International Conference on...· 0 citations