Language Model-Guided Search Heuristics

Conflict-graph search can stagnate despite effective operators when interventions fail to address the conflicts blocking progress. A disruptive intervention may also require further search before its value emerges. We propose CIPHEUR, a large language model (LLM)-guided framework that connects conflict evidence to coordinated intervention and recovery through Structured Intervention Units (SIUs). The shared control interface supports offline synthesis of executable policies and online contextual decisions. Asynchronous online control sustains native search during inference, while all policies preserve the original objective and feasibility constraints. Across eight satellite-ground scheduling conflict views with five runs per view and a 900-second evaluation cap, CIPHEUR-online achieves the highest mean objective among 11 configurations and increases mean scheduled contact duration by 14.84% over the greedy baseline GWMIN. It exceeds the strongest external per-view mean in seven of eight views and outperforms CHILS in all 40 paired runs. Within the same runs, its normalized objective improvement from 360 to 900 seconds is 1.50 to 1.86 times that of the two programmatic controllers. A separately frozen, one-shot LLM-generated controller also improves the mean objective over CHILS without runtime model calls. Together, these results demonstrate how structural search control translates LLM design knowledge and contextual reasoning into improved solution quality and sustained search progress.

Query-agnostic streaming video understanding requires vision-language models to continuously compress an indefinitely growing visual stream into a bounded memory before future queries are known. The performance depends critically on the memory mechanism--what observations to preserve, how to represent and consolidate them, and what information to retrieve when a query eventually arrives. Rather than designing a single memory architecture by hand, we formulate memory design as a search problem over executable memory programs. We introduce a lightweight domain-specific language that expresses memory mechanisms through structured primitives for representation, admission, retention, consolidation, budgeting, and retrieval, while enforcing causal and bounded-memory constraints. Although structured, the derived program space remains large and contains heterogeneous, conditionally dependent design choices whose effects can only be assessed via downstream execution. We therefore propose MemEvo, an LLM-driven auto-research framework that uses pretrained LLM as a semantics-aware proposal model to iteratively generate and refine candidate memory programs based on accumulated experimental feedback. At runtime, a deterministic evaluation pipeline validates and evaluates each candidate, while the underlying vision-language model remains frozen throughout discovery. We finally produce a training-free, bounded-memory mechanism. Extensive experiments on StreamingBench and OVO-Bench demonstrate strong streaming video understanding performance together with substantial context and inference efficiency.

Autonomous agents that automatically build artificial intelligence (AI) models could broaden access to AI across science and engineering. A popular line of such agents frames model building as a code search problem and solves it by tree search, in which each node is a candidate program and the tree grows by generating a child program from a parent, and these agents now approach the capability of experienced AI engineers on realistic benchmarks. However, these agents have three weaknesses in efficiency that have not been fully addressed. First, only a small number of candidates can be executed within a realistic budget, so search rules that rank nodes by executed rewards, such as Monte Carlo-style tree search, rely on few and noisy scores and select the next node to explore less effectively. Second, no resource-aware strategy is used to schedule training jobs, which can lower hardware utilization and training efficiency. Third, every agent call is served by a single powerful model, which inflates inference cost. Here we introduce AIBuildAI-2.5, an agentic system that carries out the tree search with LLM agents and addresses each of the three issues. AIBuildAI-2.5 proposes a novel LLM-guided tree search, in which a judge scores each candidate on its expected improvement, grounding, and feasibility, and a selector ranks the pool of candidates from these scores and the state of the search. In addition, AIBuildAI-2.5 comprises a scheduler that launches training jobs with the current hardware resource status taken into account and a router that assigns lower-cost LLMs to less demanding tasks while reserving the most capable LLM for the most challenging sub-tasks in the AI model building workflow. AIBuildAI-2.5 ranks first on MLE-Bench with a medal rate of 73.3%, and outperforms a strong baseline on six autonomous AI research tasks from AIRS-Bench.

Complex systems, core objects of study in artificial life, model diverse phenomena through nonlinear, feedback-driven interactions that produce emergent behavior, with applications from population dynamics and biology to economic policy and strategic decision-making. Yet the difficulty of predicting how feedback structure gives rise to emergent behavior, a central open problem in artificial life, makes goal-directed design exceptionally challenging. In established practice, system structures are written in specialized modeling languages such as DYNAMO or STELLA, compounding the challenge with labor-intensive workflows that limit adoption and hinder timely decision-making. To address these challenges, we introduce CEDAR, an autonomous method that uses Large Language Model (LLM) agents to discover complex systems satisfying user-specified behavioral goals. Our key innovation is an LLM-driven Monte Carlo Tree Search (MCTS) deeply coupled with complex systems: at each iteration, an LLM Judge evaluates emergent behavior against specified goals and an LLM Editor proposes improved variants, with the Judge acting as a fitness function and the Editor as a variation operator, akin to a generate-and-evaluate loop in evolutionary computation. We represent complex systems as a restricted, runnable subset of Python with domain-specific primitives, letting LLMs modify system dynamics directly. CEDAR formalizes this as an MCTS variant with an LLM-parameterized transition kernel and value function, enabling goal-directed discovery of complex system behaviors while preserving solution diversity, and its LLM-based interpretability reveals how structural changes drive emergent behavior. CEDAR reduces human effort while enabling capabilities difficult to achieve with existing approaches, facilitating broader adoption of complex systems across domains.

Reasoning about relational structures remains a significant challenge for neural models, particularly when they must systematically apply learned knowledge to problem instances that are harder than those seen in training. Progress is hampered by the difficulty of evaluating such generalization, since a priori, it is rarely clear what makes an instance hard. We study how this issue can be addressed by using large language models (LLMs) to automate benchmark generation, learning to produce increasingly challenging instances in an end-to-end manner. Concretely, given a world parametrized by Datalog rules, and an Edge Transformer as the reasoning evaluator, we use LLM-driven evolutionary search (based on FunSearch) and autonomous agentic search to discover sampling functions that yield hard problem instances. We also show that the Edge Transformer can be improved using this data such that it generalizes well to further data perturbations. Finally, we show that the same machinery can be applied to novel worlds proposed by LLMs, opening the door to autonomous research on neural relational reasoning.

Finding the shortest path in non-geometric network graphs, where edge weights encode arbitrary metrics such as latency or monetary cost rather than spatial distance, poses a challenge for informed search algorithms. Their efficiency depends on an informative heuristic, typically supplied in spatial domains by geometric distances that have no counterpart on non-geometric graphs. We propose a large language model (LLM)-aided A* algorithm in which an LLM generates intermediate waypoints that guide the A* expansion toward promising graph regions. At the core of the approach are landmark distances, which serve both as an admissible landmark-based (ALT) heuristic for the search and as a compact structural feature that, supplied to the LLM, restores the distance-to-destination signal it would otherwise lack on non-geometric graphs. Our comprehensive experiments on multiple graph topologies with up to 2,000 nodes demonstrate that LLM-generated waypoints reduce the number of expanded nodes by around 50% while incurring only a marginal path cost increase compared to the optimal solution. We further analyze the impact of prompt engineering and show that incorporating compact structural features, namely heuristic estimates, is more effective than advanced prompting techniques. These findings demonstrate the potential of combining LLM- based guidance with classical search algorithms for efficient network optimization.

Scientific discovery can be formulated as an iterative search process over the space of hypotheses and experiments. Contemporary methods navigate this space using heuristics such as MCTS. These algorithms conflate the merit of a hypothesis with the quality of its experimental execution. A promising hypothesis with preliminary execution is therefore ranked below a modest hypothesis whose execution is refined. Moreover, prior methods prune the search logs as the search progresses because the accumulated history outgrows the context window. We propose Agentic Reasoning for Tree Search (ARTS), where we deploy a reasoning language model to navigate this space. The model inspects prior execution logs, diagnoses whether earlier failures arose from faulty implementations or bad hypotheses, and selects the hypothesis to build on next. To mitigate challenges with context length, ARTS uses test-time training to instill the knowledge of search tree in the model weights. Across 22 tasks from MLGym and MLEBench, we show that ARTS outperforms leading algorithms, with over 15.3% relative improvement in the normalized score. With test-time training we show that a Qwen3-4B agent can match performance with closed-source frontier models like Gemini-3 Pro and GPT o3-reasoning with upto 5x lower inference cost. We further observe that on partially observable RL tasks, the test-time trained Qwen3-4B scientist surpasses ARTS with the o3 scientist by rediscovering the human-best recurrent-memory solution that heuristic methods prune away.

Probabilistic forecasting of infectious diseases is crucial for public health monitoring and preparedness but has historically relied on labor-intensive manual model curation by expert modeling teams. Bespoke development is an obstacle to scaling models to granular geographic resolutions or emerging pathogens. Here, we prospectively evaluate Empirical Research Assistance (ERA), an autonomous system that uses Large Language Model-guided tree search to iteratively generate, evaluate, and optimize executable forecasting software. ERA was primarily prompted with methodological approaches to implement, while in some instances it was tasked with developing forecasting approaches from scratch. In a fully prospective, real-time evaluation during the 2025-26 United States respiratory season, ERA generated methodologically diverse models for influenza, COVID-19, and respiratory syncytial virus (RSV). Aggregating a selection of these automatically-generated models yielded an ensemble that ranked first overall in official Centers for Disease Control and Prevention (CDC) post-season evaluations and outperformed the gold-standard CDC forecast ensembles across all three pathogens in a real-time prediction challenge. Additionally, ERA successfully navigated data-scarce scenarios for RSV. Controlled retrospective ablations allowed for additional explorations of the impact of optimization target and instruction-following on forecast accuracy. Preliminary experiments indicate that ERA's search optimization metric influences behavior of output forecasts, and using higher-tier language models in-search improves predictive performance. By autonomously generating interpretable code that creates epidemiologically relevant predictions, this framework provides a path toward rapidly scaling high-quality disease forecasting.

HTN planning is a variation of classical planning where, instead of searching for a linear sequence of actions, an algorithm decomposes higher-level tasks using a method library until only executable actions remain. On one hand, this allows one to introduce domain knowledge that can speed up the search for a solution through the method library. On the other hand, it creates challenges that go beyond those of classical state-space search. While recent research produced a number of heuristics and novel algorithms that speed up HTN planning, these heuristics are not yet as informative as those available in classical planning algorithms. We investigate whether large language models (LLMs) can generate effective search heuristics for HTN planning, extending the methodology of Corrêa, Pereira, and Seipp (2025) from classical to hierarchical planning. Using the Pytrich planner on six standard total-order HTN benchmark domains, we evaluate heuristics generated by nine LLMs under domain-specific prompting and compare them against the TDG and LMCount domain-independent baselines and the PANDA planner. Our results show that LLM-generated heuristics nearly match the coverage of the best available HTN planner, while substantially reducing search effort on 83% of shared problems.