LLM Planning

We introduce a self-improvement loop for reasoning models based on the following observation: Even when the difficulty of a problem exceeds the model's current solving abilities, an additionally supplied solution might enable the model to extract useful solution ideas in hindsight. We operationalize this by jointly training the same model to exhibit the following three capabilities: predicting solution ideas from problems alone, reverse-engineering ideas from problems and known solutions, and solving problems using provided ideas. The loop alternates between reverse engineering such ideas from problems with supplied solutions and using these ideas as additional supervision for joint training of all three capabilities. We give a formal specification of our method and a concrete instantiation for interactive theorem proving in the Lean theorem prover; empirical evaluation remains future work.

Planning is increasingly important for long-horizon agents, where successful execution requires coordinating subgoals, tool use, and intermediate outcomes over many steps. Yet assumptions made during planning may be invalidated by the environment, tools may return unexpected results, or actions may fail. Effective agents must therefore not only generate plans, but also revise them. Such revisions often affect only part of a plan, leaving the preceding and subsequent structure intact. Rather than regenerate the entire plan and risk unnecessary changes, repair can regenerate the affected region conditioned on the preserved prefix and suffix. We introduce Plan-and-Patch, a plan-and-act framework in which a diffusion language model (dLLM) generates a structured, program-like plan through parallel unmasking and repairs it by filling in selected regions while keeping the surrounding steps fixed. We compare DreamReasoner-8B and Qwen3-8B as diffusion and autoregressive (AR) planners. On Natural Plan without task-specific training, diffusion (53.7%) achieves nearly twice the plan repair success rate of AR (27.0%). After task-specific training on agentic benchmarks, ALFWorld and TextCraft, the planners achieve similar observed success in plan generation, while diffusion reduces mean plan-generation latency by 39-46% relative to AR. Our results show that Plan-and-Patch provides a framework for faster plan generation and effective plan repair in long-horizon agents.

Direct Preference Optimization (DPO) treats all constraint violations equally: a $1 budget overshoot and a$1,000 overshoot induce the same training signal. It is also susceptible to length and style bias when preference pairs come from different model families. We introduce Constraint-Margin DPO (CM-DPO), which replaces DPO's binary preference signal with a continuous margin derived from a deterministic symbolic verifier and scaled by violation severity. Hard and soft constraints are separated through a lexicographic objective, ensuring hard constraints are never traded off against preferences. To supply CM-DPO with bias-reduced training pairs, we generate preference data through procedurally generated constraint profiles (DCCG) and minimal-edit distillation from a reasoning teacher (RT-MED), within a framework we call SynPlan-R. On TravelPlanner, NaturalPlan, and out-of-distribution PlanBench, an 8B model fine-tuned with CM-DPO achieves 89.2% pass rate and 93.4% solve rate, matching multi-agent systems at 13x lower latency while outperforming GPT-4o on unseen Blocksworld by 9.2 points.

Frontier large language models (LLMs) can generate heuristic functions that guide search to achieve state-of-the-art performance in satisficing planning, where any plan is acceptable. However, these heuristics are not guaranteed to be admissible and can lead to suboptimal plans. We introduce LeanPlan, the first planning system that finds optimal plans with LLM-generated heuristics whose admissibility is machine-checked. Given a domain description and training tasks, an agentic loop uses planner feedback to iteratively improve a reusable domain-specific heuristic, its admissibility proof and the required domain assumptions. LeanPlan implements the heuristic, its proof and an efficient planner with machine-checked grounding and search in Lean 4. We evaluate LeanPlan on ten domains from the International Planning Competition and three new domains, using test tasks with up to 57 times as many objects as the training tasks. With GPT-5.6 Sol in the agentic loop, we successfully generate heuristics and admissibility proofs for all these domains. With the resulting heuristics, LeanPlan usually expands fewer states than the state-of-the-art Scorpion planner and solves more tasks overall.

Spacecraft rendezvous and proximity operations (RPO) are currently planned through an expertise-intensive process in which engineers translate high-level operational intent into safe, dynamically feasible trajectories, creating a bottleneck to scalable operations. Large language model (LLM)-based agents could offer an intuitive interface for this process, although their outputs are not inherently grounded in orbital dynamics, operational constraints, or the structure of admissible spacecraft maneuvers. To exploit their semantic reasoning while ensuring the generated plan's physical validity, this paper presents a hierarchical framework for spacecraft task-and-motion planning (TAMP) that grounds LLM reasoning in a graph of reusable behaviors and domain-specific planning modules. Within this framework, a pretrained LLM maps a natural-language command to a partial mission specification. The associated planners then resolve unspecified decisions within the admissible operational space. Finally, trajectory optimization converts the completed mission specification into a dynamically feasible trajectory. Numerical experiments demonstrate that this architecture substantially improves intent recovery over direct LLM generation, achieving 98% exact recovery of partial mission specifications across all evaluated splits when backed by frontier LLMs. Additional test-time-compute experiments show that, for a compact 9B model, verifier-guided revision increases exact recovery from 75% to 88%, while broader behavior-plan search independently improves selection among admissible trajectory realizations. Overall, these results establish a scalable and auditable foundation for language-driven agentic planning of spacecraft RPO.

While LLMs show promise in general reasoning, symbolic planning in chemistry remains a bottleneck. Direct ''SMILES-to-PDDL'' attempts fail because they force models to juggle chemical analysis and planning-language structuring simultaneously. We hypothesize that this failure stems from a lack of intermediate abstractions rather than insufficient model capacity. By decomposing retrosynthesis into molecule mapping, reaction mapping, and PDDL generation, we achieve high success rates where end-to-end approaches fail. This provides evidence that a primary bottleneck lies in representation alignment rather than raw model capacity. Our structural analysis demonstrates that intermediate representations are essential in retrosynthesis planning, highlighting the importance of representation-centric design in future systems.

Multimodal data analysis, which answers questions over relational tables, text, and images, has attracted growing attention in the data management community. Large language models (LLMs) enable such analysis in natural language by generating analysis plans over relational and semantic operators. However, LLM-generated plans are error-prone: a plan may silently compute something other than what was asked, fail during execution, or return a result that misses the question. This paper presents WeaveData, a multimodal data analysis system with self-critiquing and self-evolving LLM plans. First, WeaveData generates a typed logical plan for each question and critiques it step by step before execution, and it checks the executed result against the question afterwards. Second, WeaveData evolves a plan that fails or misses the question: it diagnoses the failure with the actual data, reuses the results that remain valid, and accumulates planning experience for later questions. Third, WeaveData grounds planning in a metadata knowledge graph of all modalities, clarifies ambiguous questions with the user, and backs every model judgment with evidence in an interactive notebook. We demonstrate WeaveData on two public multimodal datasets.

When a user changes their mind partway through a task, an agent that has already split the task into sub-goals and paid for tool calls must decide, per cached sub-result, whether to keep, patch, or discard it (salvage), restarting wastes valid work and continuing unchanged answers the old question. Our main finding is that salvage quality is a matter of role design rather than model capability: a language model asked the keep/patch/discard question one node at a time is unreliable, but asked to classify the revision once, with a deterministic layer propagating the decision, it reaches the cost-optimal oracle on all three models tested, from two vendors. Modeling the plan as a commitment hierarchy and the intent change as a belief-revision operator with AGM style postulates, we prove that no policy observing only a node's local view can be both safe and cost optimal, while the single classification design is both. Across three environments the policy recovers the full achievable savings, 43% cheaper than restart, at 100% correctness.

Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity increases. We address the challenge of generating high-quality natural language executable plans for complex tasks by introducing $\textbf{GRASP}$, a strategy-aware, multi-stage planning framework. GRASP decouples the planning pipeline across specialized, context-isolated modules: it pre-compiles global macro-guidelines (GenPlan), explores alternative localized strategies within isolated context windows (RevPlan), and independently evaluates trajectories using a multi-criteria discriminator (VerPlan). Empirical evaluations show that GRASP consistently establishes a new state-of-the-art frontier across diverse datasets, yielding substantial accuracy gains over direct LLM planners on Natural Plan Calendar Scheduling ($\sim$12.4\%$$\uparrow), ZebraLogic ($\sim$30.8\%$$\uparrow), and SciBench Math. Crucially, under multi-task scaling-where standard planners suffer immediate performance collapse-GRASP completely flattens the multi-task degradation penalty. In interleaved dual-task environments, GRASP achieves an absolute accuracy gain of up to 16.7$\%$ over direct LLM planners. Furthermore, by isolating context and enforcing strict macro-regularization, GRASP outperforms frontier reasoning models (such as GPT-5-mini) by a margin of 14.5$\%$.

Learned context planning selects evidence atoms before an answer model reasons over them. We test whether this learned selection improves long-context multiple-choice QA after strong retrieval, routing, budgeted-selector, and reranking controls. Our primary diagnostic uses all 503 LongBench-v2 MCQ questions with Qwen2.5-7B-Instruct. The planner is SFT-trained on outcome-selected traces from 140 training and 28 development questions; because the 503-question analysis includes those questions, it is partly transductive. At an 18k-character budget, anchored hybrid retrieval reaches 36.18% accuracy and BM25 reaches 35.98%, while the best direct planner-guided method reaches 34.19%. On the untouched 152-question test split, anchored hybrid remains higher (42.11% versus 36.84%). Leakage-safe routers cannot convert a large oracle gap. Under tight budgets, the best planner is ahead by only 0.40 points at 6k and loses at 9k; planner-guided reranking has a +1.79-point estimate at 6k with a paired interval crossing zero and ties the control at 9k. Packing-order and score-flatness analyses did not identify a stable mechanism. Under this setup, learned planning is a weak relevance signal rather than a replacement for strong retrieval.

The economic value of inference depends on how capacity and task information are distributed across stages of AI production. We study these organizational margins using controlled workflow experiments on externally verified software-engineering tasks. In two matched resource panels, direct execution records the same success rate of 59.6 percent at logical-token ceilings of 12,000 and 24,000, while success under information-constrained planning rises from 36.2 to 51.2 percent. The planning disadvantage narrows by 15.0 percentage points (95 percent task-cluster bootstrap interval: 4.2 to 25.8). A strict read-only planning campaign varies whether the planner sees the task issue. At 12,000 tokens, issue access raises success by about 16 percentage points over issue-hidden planning. Compared with direct execution, task-informed planning is about 10 points lower at 12,000 tokens; at 24,000 tokens, it shows a 29.6-point advantage. In the resource panels, direct execution uses substantially less than either ceiling, while the planning workflow's binding rate falls from 46.2 to 0.8 percent and downstream execution accounts for 89.9 percent of the increase in total use. Scale determines the capacity available to a system; workflow and information structure shape the productive value

Travel-planning agents generate itineraries that may become infeasible after acceptance because of flight cancellations, hotel unavailability, or attraction closures. Revising these itineraries involves full replanning, classical plan repair, and LLM-based travel-agent revision, whose differing task formulations and evaluation protocols hinder comparison. We conduct a systematic empirical study using two TREK-derived benchmark sets: 500 single-disruption cases, including feasible and infeasible instances, and 200 feasible simultaneous compound-disruption cases. We compare LLM-Z3 full replanning, IPyHOPPER hierarchical repair, and an iTIMO local-revision adapter across effectiveness, plan stability, and computational cost. LLM-Z3 with Gemini achieved the highest observed compound-disruption success. IPyHOPPER nearly matched that configuration's single-disruption overall success, while preserving substantially more of the accepted itinerary on successful repairs. Successful hierarchical and local repairs made fewer edits and retained more accepted commitments than full replanning. Computational profiles differed: IPyHOPPER used no LLM inference, the evaluated LLM-Z3 adapter used compact one-call inference, and the iTIMO adapter consumed substantially more tokens. The study provides practical guidelines for balancing feasibility recovery, commitment preservation, and computational cost within evaluated settings.

Adaptive learning systems commonly formulate learning path planning as Exercise-Centric (EC) recommendation, where the next step is inferred from item-level interaction logs. Evaluating goal-oriented guidance additionally requires explicit learner goals and curriculum-scale prerequisites: learners with similar exercise records may need different paths toward their targets. We therefore study Knowledge-Centric (KC) personalized learning path planning, where a planner must reason over learner profiles, mastery states, and prerequisite knowledge structures to decide which textbook, unit, and concept should be studied next. To support this setting, we introduce PersonaPath, a benchmark that pairs 2,000 fine-grained learner personas with a hierarchical knowledge graph of 347 textbooks, 1,751 units, and 4,092 concepts across 77 subjects. We evaluate representative LLMs on PersonaPath. Results show that even the strongest LLM reaches only a 29.5% final pass rate in Basic Education, and that the main bottleneck lies in adaptivity, where no model exceeds 44.7% in tailoring paths to individual learners.

Bridging the gap between human intent and machine execution remains a challenge in automated planning, where expressing goals in formal languages like PDDL restricts accessibility to non-experts. This paper empirically evaluates whether current Large Language Models (LLMs) can reliably translate natural language testing goals, written in informal language by video game testers, into well-formed PDDL targets suitable for classical planning. We present a carefully designed prompt template, integrating insights from iterative experimentation, aimed at maximizing both accuracy and response coherence from multiple state-of-the-art LLMs. Six contemporary models are systematically assessed on correctness, speed, and error tendencies using real-world, domain-specific benchmarks. All models demonstrate high correctness, exceeding 92%, with Gemini 2.5 Flash achieving the highest accuracy at 96% and the lowest incidence of false positives, while GPT-4.1 leads in response speed. Despite these advances, critical distinctions exist in model performance, and occasional failures arise from language ambiguity and limitations in domain representation. Our analysis underscores both the significant progress and ongoing gaps in enabling LLMs to act as robust bridges between natural language objectives and automated planning pipelines.

Lindsey et al. (2025) report that Claude 3.5 Haiku plans rhymes: features for candidate rhyme words are active on the newline before a line is written, and a suppress-and-inject intervention redirects the line only when applied there (their Figure 13). We test how far this generalizes on seven cells crossing four open models (0.6B to 2.6B parameters) with six open cross-layer transcoders (CLTs), on one consumer GPU, decomposing the claim into position specificity (C1), newline site identity (C2), and a newline-resident plan (C3). This is a stress test rather than a faithful reproduction: attribution graphs are unavailable for these CLTs, so features are found bottom-up from decoder vectors. C1 generalizes, in every cell and in all 247 of 444 prompt-by-inject pairs with a detectable effect, but the effective position is the final prompt token, adjacent to emission, and only two cells reach behaviorally meaningful probabilities. C2 and C3 are not recovered by any probe: a census of every active feature finds no rhyme-anticipating enrichment at the newline, and steering the newline while the model composes the whole line, over 36 runs and 8,640 sampled lines, shows why. That intervention is strong but one token long, making the injected word the first word of the composed line in 703 of 720 samples and leaving the rhyme six words later untouched. A final test drops the transcoder entirely: patching the newline's whole residual, at every layer, from a minimal-pair poem whose third line ends on a different rhyme moves the rhyme in 11 of 1,260 composed lines against 4 at baseline, with a design resolving 1.4%. We read this as a boundary condition rather than a refutation: at this scale and with these transcoders, the causal site is emission-adjacent. We reproduce Figure 13's shape, not its mechanism. Code and data are public (code: github.com/PCfVW/poetry-planning-site).

Large Language Models (LLMs) have shown promise for translating Natural Language (NL) planning descriptions into PDDL problem instances. However, standard evaluation criteria such as syntactic validity or planner success can substantially overestimate faithfulness to the described task: a generated problem may be parseable and solvable while misrepresenting the intended initial state, goal, object structure, or optimization target. This paper studies an end-to-end NL-to-PDDL pipeline that combines LLM generation, checks in terms of PDDL parsing, planning and validation, a domain-conformance checker, an LLM critic, and iterative repair. Fine-grained repair feedback is constructed from the domain description, the generated problem, the natural language problem description, and operational diagnostics. Reference-based comparisons against curated benchmark PDDL problem descriptions are used for post-hoc benchmark analysis, and these offline checks include renaming-invariant structural matching and semantic equivalence, where domain support is available. Across Planetarium, AutoPlanBench, and curated PDDL2.1 problems, results show that operational success and benchmark-reference reconstruction can diverge substantially. Results also show that structured repair can be useful, and that PDDL2.1 remains challenging for reference reconstruction, even when operational success improves.

Large Language Models (LLMs) have recently demonstrated strong capabilities in automated travel itinerary generation. However, real- world travel planning is inherently uncertain: transportation delays, crowd fluctuations, and unexpected stochastic delays frequently inval- idate otherwise feasible schedules. Existing benchmarks like TravelPlanner and TripCraft assume deterministic environments, evaluating only static constraint satisfaction and ignoring whether generated plans remain robust when such uncertainties arise. To address this limitation, we introduce UTP-Bench1 , a large-scale benchmark for uncertainty-aware travel planning. The dataset integrates real-world travel data spanning 504 cities of India, including attractions, restau- rants, accommodations, and multi-modal trans- portation networks. To model realistic disrup- tions, UTP-Bench incorporates empirical delay distributions and crowd-density patterns col- lected from major cities, enabling evaluation of travel plans under stochastic conditions. We further propose three evaluation metrics, namely Buffer Adequacy Score (BAS), Crowd- Aware Timing Score (CATS), and Transport Delay Absorption Score (TDAS), which quan- tify the ability of generated itineraries to main- tain robustness against transit delays and crowd variability. Experiments with state-of-the-art LLMs like GPT-5, Qwen3, Mistral and Phi-4 re- veal substantial gaps between model-generated and human-authored plans, particularly in tem- poral buffering, delay-aware transportation scheduling, and crowd-sensitive planning.

Reliable planning requires converting natural-language instructions into executable symbolic specifications, yet large language models remain brittle without costly PDDL annotations and may exploit solver success in semantically unfaithful ways. We study how to learn faithful natural-language-to-PDDL formalization using only solver feedback, without human-written demonstrations. We propose a solvergrounded multi-role reinforcement learning framework where a single language model acts as an Actor, Judge, and Editor for generation, verification, and repair. The Actor proposes PDDL specifications, the Judge provides a solver-calibrated quality signal, and the Editor performs bounded diagnostic-conditioned refinement. On PlanBench, our method improves average success from 35.5% for LLM+P to 70.8%, achieves 66.3% faithful success, and reduces semantic drift to 6.4%. These results show that organizing solver feedback into generation, verification, and repair roles enables more scalable and faithful annotation-free symbolic planning

World Action Models (WAMs) jointly predict future actions and the evolution of the environment. At each inference, a WAM generates a chunk of actions and the robot executes a fixed prefix before replanning. We argue that this fixed execution horizon is poorly matched to execution dynamics: the chunk reliability varies across task stages, so when to replan depends on the result of accumulated execution, not on the step counts. We propose TempoWAM (Timing Execution by Monitoring Progress Online), a lightweight plug-and-play execution scheme for WAMs. A Recurrent Progress Monitor first estimates task progress from the current observation, task instruction, remaining actions, and execution history; and an Adaptive Execution Protocol then evaluates whether the chunk is advancing the task to decide if replanning is needed. To bridge the training-deployment gap, the protocol is calibrated by a task-dependent calibration factor with online adaptation. Experiments on LIBERO, RoboTwin, and real-world tasks show that TempoWAM consistently improves the efficiency-success trade-off of WAM execution. On real robots, it reduces WAM inferences by 26.9% on easy tasks while maintaining success, and improves success by 13.3 points on difficult tasks.

The Tower of Hanoi is a simple planning puzzle that in prior work has proven challenging for large reasoning models (LRMs). Current models solve the standard formulation of the puzzle, but still struggle with the flat-to-flat variant (where initial and goal states are not restricted to have all rings on a single peg). This paper presents an in-depth study of how both small, in-house Transformers and large, third-party LRMs solve this task. To understand the failures mechanistically, we first train small Transformers from scratch on precomputed solution traces. Using a variety of interpretability techniques, we show that these Transformers develop an emergent world model: a linearly decodable, geometrically faithful representation of the puzzle's state space (the Sierpinski triangle), that is causally involved in solving the puzzles. Second, we return to the large LLMs and apply our techniques to two frontier reasoning models, Qwen3.6-27B and DeepSeek-R1-Distill-Qwen-32B, that attempt to solve the task through extended chain-of-thought. Surprisingly, we find that both models encode the Sierpinski world model near-perfectly at the end of the prompt, and yet fail at the majority of tasks when there are more than 3 rings. We locate the source of this failure in the decaying representation of the world model. We probe for the representation at different stages during planning, and establish causality by showing that performance can be improved by injecting the prompt-time representation at inference. The failure of the models is thus one of maintenance of the required representations, not their absence, and performance is at least partially recoverable. These results thus reframe the reported collapse in performance from prior work: current Large Reasoning Models build a world model, and then lose it.

LLM-agent evaluations commonly measure task success or agreement with a declared plan. In strategic cyber-physical systems, an architecture must also remain appropriate after autonomous participants respond and physics constrains outcomes. We introduce a controlled benchmark of planning-induced control trajectories: ordered planning operations and directives linking execution architecture to strategic response and physical consequences. Four coded executors (predefined, sequential, hierarchical, and search) control demand response for 40 prosumers on a radial feeder. The LLM declares or advises typed policies and mediates communication; schedules, base prosumer dynamics, stochastic actions, and power flow remain explicit code. Paired forced-mode counterfactuals, exact-prompt caching, common response draws with separate randomness streams, critic isolation, and event-level feasibility isolate comparisons. The Llama-3.3-70B experiments on this feeder distinguish three properties. First, forced search is the oracle in all five baseline seeds under the specified objective. Second, injected objective substitution preserves mode agreement at 1.0 while increasing cumulative voltage shortfall by 2.68x. Third, the 144-scenario, 576-episode factorial bank, using three repeated seeds, contains feasible oracles from predefined, sequential, and search. The prespecified stress-held-out ridge has mean regret 90.7 and no observed value over fixed sequential. A post-hoc constraint-aware analysis reduces regret to 29.0; a simple deadline rule attains 28.7, so this gain does not establish a learning advantage. An all-feasible ablation does not improve over fixed search. These are simulation-internal, descriptive comparisons. A five-model, 300-declaration extension tests interface behaviour, not cross-backbone physical rankings; shared-endpoint latency tails motivate probabilistic live feasibility.

Multilingual multi-agent systems exhibit substantial degradation beyond English, yet prior work rarely identifies how task-critical information is lost when user requests are converted into executable plans. We study the planner in a multi-agent system as the request-to-action interface and derive an actionable taxonomy of planning-grounding failures from failed real-world task executions. LLM-based analysis shows that these failures constitute an increasing share of unsuccessful executions as language-resource availability declines, with the strongest effects in low-resource languages. To test whether the taxonomy supports mitigation, we introduce TART, Taxonomy-Guided Actionable Representation, that makes the taxonomy's key aspects explicit to the planner and downstream sub-agents. Across multiple languages, three LLM backbones, two datasets, and two agentic configurations, TART consistently improves performance. On multilingual GAIA, it raises a state-of-the-art system's accuracy by 5.6 percentage points averaged across eleven languages spanning low- to high-resource settings.

LLM-based multi-agent coordination faces a fundamental trade-off between efficiency and adaptivity in dynamic environments. Existing approaches typically rely on repeated LLM invocations or multi-round communication to adapt decisions during execution, introducing substantial latency and making coordination vulnerable to asynchronous progress and environmental changes. Conversely, one-shot planning reduces coordination overhead but produces open-loop plans that can quickly become stale or fail when actions depend on other agents and the environment. We introduce SyncPlan, a plan-execute-correct framework for long-horizon coordination through explicit synchronization and adaptive correction. Given the state and team-level task, a centralized LLM coordinator generates per-agent action chains in a single planning call. During execution, explicit wait primitives and deadlock detection enforce inter-agent and agent-environment dependencies, while a lightweight Plan Staleness Detector continuously assesses the remaining plan and triggers replanning when environmental changes invalidate its assumptions. We further optimize the coordinator through SFT and planning-oriented RL with dense task progress and outcome-level execution feedback. Experiments on the public Overcooked benchmark and the complex Honor of Kings environment show that SyncPlan achieves state-of-the-art task success rates while using less than 0.05% of the wall-clock runtime compared with existing LLM-based coordinators. Code and datasets will be made publicly available.

Multi-turn long-horizon planning is critical for foundation model agents, yet how to fundamentally improve it remains unclear. Existing models are trained on uncontrollable and opaque Internet data, making it difficult to identify how planning ability is acquired, shaped, and integrated. To address this challenge, we introduce a unified and controlled multi-turn environment that enables precise control. It allows systematically study long-horizon planning across three stages. (1) Planning ability acquisition during pre-training. We study data format, distribution, and quality. Explicit world model construction through CoT state transition modeling yields stronger long-horizon generalization. Atomic skills alone are insufficient for compositional generalization, whereas a litte long-horizon data works. Moreover, suboptimal trajectories severely impair performance because errors amplify over long horizons. (2) Planning ability shaping via GRPO and OPD post-training. Through mutual information, we distinguish general planning patterns from task-specific planning knowledge. For planning patterns, we identify three application regions of post-training: unnecessary, effective, and unsupported. OPD has a broader effective region than GRPO under low-quality and long-horizon settings, as it provides more consistent update directions. For planning knowledge, distilling unseen procedures from a teacher with different knowledge may impair student's prior world modeling without fully establishing new knowledge. (3) Planning ability integration through MOPD post-training. We show that multi-teacher on-policy distillation (MOPD) integrates capabilities by converging to shared planning-pattern across environments. Compatible patterns enable cross-environment generalization, partially shared patterns support continual learning, while completely conflicting patterns cause severe interference.

This paper proposes AI Tour Meeting, a group travel planning framework powered by multiple Large Language Model (LLM)-based agents. The agents are instantiated with distinct personas and collaboratively seek an itinerary that satisfies their constraints and preferences through natural language discussion. The framework enables easy and flexible orchestration of such discussions by providing interfaces for configuring agent personas, discussion workflows, monitoring, and LLM deployment. Its primary use case is a simulation tool for analyzing the behavior of multiple LLM agents during tour planning discussions. This paper demonstrates the utility of the framework by presenting system validation and several analytical results obtained by the framework.

We present MagicSelector, a joint optimization framework integrating Counterfactual task decomposition, Progressive reranking, and Dynamic Top-K, designed to address the fundamental challenges of tool retrieval in agents. MagicSelector is a specialized framework capable of translating ambiguous user instructions into executable atomic subtasks and guiding high-precision tool retrieval, effectively mitigating redundant noise and severe context distraction in out-of-domain (OOD) scenarios. We empower MagicSelector with these capabilities through three key contributions: (1) a preference-guided counterfactual task decomposition mechanism that utilizes a counterfactual reward to quantify the marginal causal gain of decomposition on retrieval ranking, effectively imposing fine-grained structural supervision on logical coherence; (2) a progressive tool reranking method driven by self-distillation hard negative mining, which optimizes both point-wise and list-wise relevance to enhance fine-grained discrimination among highly similar tools; and (3) a dual semantic boundary-aware dynamic Top-K strategy that adaptively monitors reranking score cliffs and inter-tool semantic shifts to dynamically truncate the candidate list, maximizing relevant tool recall while filtering long-tail noise. Evaluated on MTDTool, the first task decomposition benchmark we constructed tailored for mobile multi-turn interactions with process-level annotations, MagicSelector yields promising performance. Extensive experiments demonstrate that MagicSelector significantly outperforms state-of-the-art methods in terms of tool retrieval accuracy, OOD generalization capability, and overall token efficiency, thereby demonstrating the effectiveness of our proposed framework.

Large Language Models (LLMs) have had a remarkable impact across many areas of machine learning. However, recent studies have shown that they struggle to reliably solve planning problems. At the same time, theoretical results have shown that transformers, the core architecture underlying modern LLMs, are Turing-complete. In this work, we investigate this apparent gap between the theoretical computational power of LLMs and their empirical planning performance. We propose Chain of Computation (COC), a computational architecture that places a transformer-based LM inside an iterative loop, leveraging its strength as a pattern-matching system. The COC uses a Structured Context Window (SCW) which provides a constant-sized context window with support for choosing which window is used at each planning step. Within this architecture, the LM is able to learn a planning policy, predicts the world model, and performs the arithmetic operations required during planning. We show that, when given an append-only SCW (resembling a Turing Machine tape), even relatively small LMs trained from scratch can learn planning policies and generalize from a small number of training instances within each planning domain, achieving success rates above 99.89% on BlocksWorld and the Pancake puzzle. Our analysis of failure cases in Tower of Hanoi (TOH) reveals that they arise from arithmetic operations or from encountering previously unseen tokens. We show that COC can solve TOH problem instances with up to 20 disks, requiring over 1 million actions, while requiring substantially less training data by either (1) planning with symbolical support for arithmetic or by (2) using a deterministic pushdown automaton (PDA) formulation for the SCW.

When LLMs exhibit uneven performance across planning tasks, these gaps are often attributed to task difficulty. We argue that this explanation is incomplete, as task-level variation may reflect distinct latent planning competencies rather than differences along a single ability spectrum. We study this question on ACPBench-Hard by evaluating multiple LLM families under varying test-time reasoning budgets and applying a multidimensional item response theory model to uncover the latent competency structure underlying LLM planning. The analysis reveals two principal dimensions that shape planning performance: operational reasoning, the ability to evaluate local action applicability and immediate state transitions, and structural enumeration, the ability to reason about goal reachability and landmark structure. Operational reasoning improving under model scaling and longer reasoning traces, while structural enumeration remains comparatively insensitive. Our findings motivate competency-level evaluation of LLM planning, shifting the focus from whether models improve overall to which planning competencies improve, under what conditions, and why.

Bridging the gap between human pilot intent and autonomous flight operation is critical for real-world electric vertical takeoff and landing (eVTOL) aircraft deployment. Flight planning traditionally relies on classic algorithms that struggle to incorporate flexible human preferences. We present FRAMe, an End-to-End Large Language Model (LLM) Flight Planning tool with RAG-based Memory and Multi-modal Coach Agent. Our system integrates a planner LLM with a multi-modal coach agent and retrieval augmented generation (RAG)-based memory to generate flight plans that satisfy mission constraints while aligning with human flight operator preferences. We demonstrate the system in a range of real-world-inspired scenarios of varying difficulty levels. Across four LLMs, the full FRAMe system (RAG and coach) yields the highest validity for every planner (up to 93.8% aggregate, 99% on Easy scenarios for the strongest planner) and shifts preference-relevant metrics in the operator-favored direction where the metric has headroom. FRAMe signifies how advanced LLMs can be deployed for human-centric mission planning, translating natural language instructions into safe, efficient, and flexible flight routes. The code is available at: github.com/amin-tabrizian/FlightPlanningLLMs

Skill usage can significantly enhance the ability of modern agent systems to complete complex tasks. However, the growing scale of skill libraries makes accurate skill selection increasingly challenging. In real-world scenarios, ambiguous semantic matching often arises between a specific task requirement and multiple generic yet semantically similar candidate skills. Moreover, existing methods tend to overlook the dynamic influence of task difficulty and skill applicability when selecting the optimal target skill set. To address these issues, we propose SkillReranker, an inference-time reranking framework for adaptive skill selection. Specifically, we first perform semantic decomposition on both the task and skill sides, yielding informative subtask and execution-state descriptions as well as transition-state descriptions that characterize each skill's functionality. These descriptions are then used to construct a directed acyclic execution graph, where intermediate task states are modeled as nodes and candidate skills as edges, thereby establishing a structured task-skill correspondence. On this basis, SkillReranker determines whether each state node satisfies the split condition to identify subtask intervals. For each task interval, we employ a cross-encoder to perform comprehensive scoring over candidate skills and select the most suitable ones to form the final target skill set. Experiments on ALFWorld and ScienceWorld with three backbone LLMs show that SkillReranker effectively improves task performance, reduces environment interaction steps, and lowers token consumption compared with existing skill selection baselines.