Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis

• URL: http://arxiv.org/abs/2605.17539v2
• Date: Tue, 19 May 2026 03:52:40 GMT
• Title: Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis
• Abstract summary: We introduce MEMOIR, a memory-guided tree-search framework with a two-level memory hierarchy.<n>Across seven Combinatorial optimization problems, MEMOIR achieves 96.7% solution validity.<n>MeMOIR's run-to-run validity standard deviation is more than an order of magnitude below that of every baseline we evaluated.
• Score: 3.0663322946413287
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Combinatorial optimization (CO) underlies decision-making from logistics to chip design, where infeasible solutions are operationally unusable and small quality gains translate into substantial economic value. Recent work uses large language models (LLMs) to automate solver synthesis: generating executable solver programs from natural-language specifications. However, existing tree-search and evolutionary agents refine candidate trajectories in parallel without explicit knowledge transfer, reintroducing the same constraint violations and converging on similar algorithm families. We introduce MEMOIR, a memory-guided tree-search framework with a two-level memory hierarchy: branch-local memory preserves execution-grounded refinement details within a branch as it iterates on a single algorithmic design, while global memory stores compressed algorithmic and failure-mode summaries across branches. A reflection step at branch termination distills these summaries, enabling cross-branch transfer without polluting future contexts with low-level debugging traces. Across seven CO problems spanning scheduling, routing, packing, and geometric design, MEMOIR achieves 96.7% solution validity (a 9.2 point gap over the strongest baseline) and improves the average normalized score by 7.3 points at matched per-method execution budget. Over three independent runs on four problems, MEMOIR's run-to-run validity standard deviation is more than an order of magnitude below that of every baseline we evaluated in this setting, suggesting that memory-guided exploration yields consistent improvements rather than reflecting sampling variance.

Related papers

• Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry [105.89493240787861]
  We introduce credit-addressable reasoning, in which semantic units exposed during inference also define where learning compares alternatives and assigns credit.<n>We instantiate this principle with Code-CoT, which represents visual relations as line-addressable executable code, and organizes reasoning into typed events.<n>Across nine geometry benchmarks, CE-GRPO achieves an average accuracy of 76.04, outperforming Qwen3-VL-8B and trajectory-level GRPO by $8.09$ and 3.43 points, respectively.
  arXiv  Detail & Related papers  (2026-08-31T08:44:36Z)
• EngiAI: A Multi-Agent Framework and Benchmark Suite for LLM-Driven Engineering Design [0.4499833362998488]
  We introduce a benchmark suite with three evaluation dimensions.<n>We present EngiAI, a Multi-Agent System (MAS) implementation built on LangGraph.
  arXiv  Detail & Related papers  (2026-05-19T12:12:09Z)
• HMACE: Heterogeneous Multi-Agent Collaborative Evolution for Combinatorial Optimization [19.90781293176099]
  HMACE is a Heterogeneous Multi-Agent Collaborative Evolution framework.<n>It decomposes each evolutionary generation into an autonomous, role-specialized loop with four coordinated agents.<n>It guides the search toward diverse and promising behaviors while avoiding redundant evaluations.
  arXiv  Detail & Related papers  (2026-05-08T04:02:28Z)
• Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees [68.04613115686509]
  Self-consistency boosts inference-time performance by sampling multiple reasoning traces in parallel and voting.<n>We propose Distinct Leafion (DLE), a deterministic decoding method that treats truncated sampling as a pruned tree and systematically enumerates distinct leaves instead of sampling with replacement.<n>DLE explores higher-quality reasoning traces, yielding better performance on math, coding, and general reasoning tasks.
  arXiv  Detail & Related papers  (2026-04-22T12:42:03Z)
• Rethinking Retrieval-Augmentation as Synthesis: A Query-Aware Context Merging Approach [8.202508647749125]
  Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to extend their existing knowledge by dynamically incorporating external information.<n>Standard pipelines address this via a retrieve-then-select strategy, typically retaining only the top-k chunks based on relevance.<n>We propose MergeRAG, a novel framework that shifts the paradigm from static filtering to query-aware synthesis.
  arXiv  Detail & Related papers  (2026-03-18T09:09:52Z)
• Understanding by Reconstruction: Reversing the Software Development Process for LLM Pretraining [66.89012795621349]
  Large Language Models (LLMs) often struggle with the deep, long-horizon reasoning required for complex software engineering.<n>We propose a novel paradigm: understanding via reconstruction.<n>We introduce a framework that synthesizes latent agentic trajectories using a multi-agent simulation.
  arXiv  Detail & Related papers  (2026-03-11T09:23:20Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• DRAGON: LLM-Driven Decomposition and Reconstruction Agents for Large-Scale Combinatorial Optimization [40.88623618289683]
  Large Language Models (LLMs) have recently shown promise in addressing optimization problems (COPs) through prompt-based strategies.<n>We propose DRAGON, which combines the strengths of metaheuristic design and LLM reasoning.<n>By continuously interacting with the optimization environment and leveraging an adaptive experience memory, the agents iteratively learn from feedback.
  arXiv  Detail & Related papers  (2026-01-10T09:31:40Z)
• MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning [73.27233666920618]
  We propose MemSearcher, an agent workflow that iteratively maintains a compact memory and combines the current turn with it.<n>At each turn, MemSearcher fuses the user's question with the memory to generate reasoning traces, perform search actions, and update memory to retain only information essential for solving the task.<n>We introduce multi-context GRPO, an end-to-end RL framework that jointly optimize reasoning, search strategies, and memory management of MemSearcher Agents.
  arXiv  Detail & Related papers  (2025-11-04T18:27:39Z)
• Once Upon an Input: Reasoning via Per-Instance Program Synthesis [19.86168542588911]
  We introduce Per-Instance Program Synthesis (PIPS), a method that generates and refines programs at the instance-level using structural feedback.<n>To further improve performance, PIPS incorporates a confidence metric that dynamically chooses between direct inference and program synthesis on a per-instance basis.
  arXiv  Detail & Related papers  (2025-10-26T21:58:33Z)
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory [0.5584627289325719]
  Large Language Models (LLMs) have demonstrated remarkable prowess in generating contextually coherent responses.<n>But their fixed context windows pose fundamental challenges for maintaining consistency over prolonged multi-session dialogues.<n>We introduce Mem0, a scalable memory-centric architecture that addresses this issue by dynamically extracting, consolidating, and retrieving salient information from ongoing conversations.
  arXiv  Detail & Related papers  (2025-04-28T01:46:35Z)
• Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories [72.15369769265398]
  Machine learning has emerged as a promising paradigm for branching. We propose retro branching; a simple yet effective approach to RL for branching. We outperform the current state-of-the-art RL branching algorithm by 3-5x and come within 20% of the best IL method's performance on MILPs with 500 constraints and 1000 variables.
  arXiv  Detail & Related papers  (2022-05-28T06:08:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.