Textual Belief States for World Models: Identifiable Representation Learning Under Strict Mediation

World models in partially observed environments rely on latent representations that summarize interaction history, but in many modern LLM-based architectures predictive performance fails to reflect representation quality due to history bypass, rendering the latent state unidentifiable. Strict latent state mediation, requiring predictions to depend only on the latent state and action, is a classical principle that resolves this, but enforcing it in text-based settings is an open challenge: textual latent states are discrete and non-differentiable, precluding variational training, and expressive LLM decoders readily ignore the bottleneck. We show how to make strict mediation work in the text domain. We formalize why it is necessary, showing that strict mediation makes representation quality empirically testable while history-leaky architectures break this connection. We then introduce textual latent states, which are discrete, interpretable, and variable-length, and factorized GRPO (fGRPO), a tree-structured reinforcement learning method that enforces strict mediation during training. Experiments on TextWorld and ScienceWorld show preserved one-step prediction accuracy alongside up to 57\% gains in representation quality and 98\% improvements in rollout performance, increasing with task complexity and horizon.

Executable Schema Contracts: From Automatic Ingestion to Multi-Source Retrieval

Real-world data spans tables, documents, and semi-structured files with implicit semantics. Querying this data requires integrating evidence across inconsistent schemas and formats, yet existing approaches either demand costly manual engineering or bypass structure entirely. We present a system that automatically discovers an executable schema from raw multi-source data and uses it as a shared contract for knowledge graph construction and query-time retrieval. A closed-world field catalog constrains LLM-based schema discovery to attested fields; deterministic structural analysis infers identity keys, foreign keys, and source hierarchy; and the resulting schema drives extraction, deduplication, and cross-source linking into a provenance-aware knowledge graph. At query time the schema -- optionally extended via a monotonic protocol -- conditions a multi-tool agent routing retrieval across structured lookup, graph traversal, and vector search, returning grounded answers with traceable citations. In controlled zero-shot comparisons using the same LLM, data, and evaluation harness, the system improves over retrieval-only and decomposition-based baselines across four QA benchmarks, with ablations showing that schema-conditioned routing, structural intelligence, and schema-guided construction each contribute to the gains.

When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories

Early failure alerting requires deciding, while a dialog or agent trajectory is still unfolding, whether to flag it as likely to fail. This is challenging because supervision is typically available only as a trajectory-level success/failure label while alerts must be raised from partial interactions. Prior early-classification methods often bridge this gap by assigning the terminal label to every prefix, treating every turn as failure evidence. We hypothesize that this prefix-label assumption is poorly matched to multi-turn language interactions, where evidence of eventual failure is sparse and often delayed. In this paper, we introduce a two-stage approach that learns from this sparse evidence structure and uses the resulting risk estimates for controllable early alerting. Specifically, our attention-based failure predictor learns sparse turn-level failure evidence from trajectory labels and uses it to estimate failure risk from partial histories. We then pair this predictor with $α$-STOP, a single preference-conditioned stopping policy that selects an accuracy-earliness operating point at inference time rather than training a separate trigger for each preference. Across five benchmarks spanning customer support, task-oriented dialog, persuasion, tool use, and planning, we first show that high-relevance failure evidence occupies only 4.7-11.3% of turns and first appears after 59.0-83.6\% of trajectories on average. We further show that the attention-based predictor improves Pareto-frontier quality (hypervolume) by 1-10\% over naive prefix supervision, and that the full system improves frontier quality by 3-42\% over state-of-the-art trigger policies while reducing training cost per operating point by 1-3 orders of magnitude.

Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use

The performance of LLM-based agents depends not only on the agent itself but also on the quality of the tool interfaces it consumes. While prior work has focused heavily on agent fine-tuning, tool interfaces-including natural language descriptions and parameter schemas-remain largely human-oriented and often become a bottleneck, especially when agents must select from large candidate tool sets. Existing approaches to improving tool interfaces rely on execution traces, which are frequently unavailable in cold-start or privacy-constrained settings, and typically optimize each tool independently, limiting scalability and generalization to unseen tools. We propose Trace-Free+, a curriculum learning framework that progressively transfers supervision from trace-rich settings to trace-free deployment, encouraging the model to abstract reusable interface-usage patterns and tool usage outcomes. To support this approach, we construct a large-scale dataset of high-quality tool interfaces using a structured workflow over a diverse collection of tools. Experiments on StableToolBench and RestBench show consistent gains on unseen tools, strong cross-domain generalization, and robustness as the number of candidate tools scales to over 100, demonstrating that tool interface optimization is a practical and deployable complement to agent fine-tuning.

REMem: Reasoning with Episodic Memory in Language Agent

Humans excel at remembering concrete experiences along spatiotemporal contexts and performing reasoning across those events, i.e., the capacity for episodic memory. In contrast, memory in language agents remains mainly semantic, and current agents are not yet capable of effectively recollecting and reasoning over interaction histories. We identify and formalize the core challenges of episodic recollection and reasoning from this gap, and observe that existing work often overlooks episodicity, lacks explicit event modeling, or overemphasizes simple retrieval rather than complex reasoning. We present REMem, a two-phase framework for constructing and reasoning with episodic memory: 1) Offline indexing, where REMem converts experiences into a hybrid memory graph that flexibly links time-aware gists and facts. 2) Online inference, where REMem employs an agentic retriever with carefully curated tools for iterative retrieval over the memory graph. Comprehensive evaluation across four episodic memory benchmarks shows that REMem substantially outperforms state-of-the-art memory systems such as Mem0 and HippoRAG 2, showing 3.4% and 13.4% absolute improvements on episodic recollection and reasoning tasks, respectively. Moreover, REMem also demonstrates more robust refusal behavior for unanswerable questions.

COMBOOD: A Semiparametric Approach for Detecting Out-of-distribution Data for Image Classification

Identifying out-of-distribution (OOD) data at inference time is crucial for many machine learning applications, especially for automation. We present a novel unsupervised semi-parametric framework COMBOOD for OOD detection with respect to image recognition. Our framework combines signals from two distance metrics, nearest-neighbor and Mahalanobis, to derive a confidence score for an inference point to be out-of-distribution. The former provides a non-parametric approach to OOD detection. The latter provides a parametric, simple, yet effective method for detecting OOD data points, especially, in the far OOD scenario, where the inference point is far apart from the training data set in the embedding space. However, its performance is not satisfactory in the near OOD scenarios that arise in practical situations. Our COMBOOD framework combines the two signals in a semi-parametric setting to provide a confidence score that is accurate both for the near-OOD and far-OOD scenarios. We show experimental results with the COMBOOD framework for different types of feature extraction strategies. We demonstrate experimentally that COMBOOD outperforms state-of-the-art OOD detection methods on the OpenOOD (both version 1 and most recent version 1.5) benchmark datasets (for both far-OOD and near-OOD) as well as on the documents dataset in terms of accuracy. On a majority of the benchmark datasets, the improvements in accuracy resulting from the COMBOOD framework are statistically significant. COMBOOD scales linearly with the size of the embedding space, making it ideal for many real-life applications.

RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule Learning

Large language models (LLMs) often struggle to use tools reliably in domain-specific settings, where APIs may be idiosyncratic, under-documented, or tailored to private workflows. This highlights the need for effective adaptation to task-specific tools. We propose RIMRULE, a neuro-symbolic approach for LLM adaptation based on dynamic rule injection. Compact, interpretable rules are distilled from failure traces and injected into the prompt during inference to improve task performance. These rules are proposed by the LLM itself and consolidated using a Minimum Description Length (MDL) objective that favors generality and conciseness. Each rule is stored in both natural language and a structured symbolic form, supporting efficient retrieval at inference time. Experiments on tool-use benchmarks show that this approach improves accuracy on both seen and unseen tools without modifying LLM weights. It outperforms prompting-based adaptation methods and complements finetuning. Moreover, rules learned from one LLM can be reused to improve others, including long reasoning LLMs, highlighting the portability of symbolic knowledge across architectures.

The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogs

Large Language Model (LLM)-based agents have significantly impacted Task-Oriented Dialog Systems (TODS) but continue to face notable performance challenges, especially in zero-shot scenarios. While prior work has noted this performance gap, the behavioral factors driving the performance gap remain under-explored. This study proposes a comprehensive evaluation framework to quantify the behavior gap between AI agents and human experts, focusing on discrepancies in dialog acts, tool usage, and knowledge utilization. Our findings reveal that this behavior gap is a critical factor negatively impacting the performance of LLM agents. Notably, as task complexity increases, the behavior gap widens (correlation: 0.963), leading to a degradation of agent performance on complex task-oriented dialogs. For the most complex task in our study, even the GPT-4o-based agent exhibits low alignment with human behavior, with low F1 scores for dialog acts (0.464), excessive and often misaligned tool usage with a F1 score of 0.139, and ineffective usage of external knowledge. Reducing such behavior gaps leads to significant performance improvement (24.3% on average). This study highlights the importance of comprehensive behavioral evaluations and improved alignment strategies to enhance the effectiveness of LLM-based TODS in handling complex tasks.

SCE: Scalable Consistency Ensembles Make Blackbox Large Language Model Generation More Reliable

Large language models (LLMs) have demonstrated remarkable performance, yet their diverse strengths and weaknesses prevent any single LLM from achieving dominance across all tasks. Ensembling multiple LLMs is a promising approach to generate reliable responses but conventional ensembling frameworks suffer from high computational overheads. This work introduces Scalable Consistency Ensemble (SCE), an efficient framework for ensembling LLMs by prompting consistent outputs. The SCE framework systematically evaluates and integrates outputs to produce a cohesive result through two core components: SCE-CHECK, a mechanism that gauges the consistency between response pairs via semantic equivalence; and SCE-FUSION, which adeptly merges the highest-ranked consistent responses from SCE-CHECK, to optimize collective strengths and mitigating potential weaknesses. To improve the scalability with multiple inference queries, we further propose ``{You Only Prompt Once}'' (YOPO), a novel technique that reduces the inference complexity of pairwise comparison from quadratic to constant time. We perform extensive empirical evaluations on diverse benchmark datasets to demonstrate \methodName's effectiveness. Notably, the \saccheckcomponent outperforms conventional baselines with enhanced performance and a significant reduction in computational overhead.

Learning to Search Effective Example Sequences for In-Context Learning

Large language models (LLMs) demonstrate impressive few-shot learning capabilities, but their performance varies widely based on the sequence of in-context examples. Key factors influencing this include the sequence's length, composition, and arrangement, as well as its relation to the specific query. Existing methods often tackle these factors in isolation, overlooking their interdependencies. Moreover, the extensive search space for selecting optimal sequences complicates the development of a holistic approach. In this work, we introduce Beam Search-based Example Sequence Constructor (BESC), a novel method for learning to construct optimal example sequences. BESC addresses all key factors involved in sequence selection by considering them jointly during inference, while incrementally building the sequence. This design enables the use of beam search to significantly reduce the complexity of the search space. Experiments across various datasets and language models show notable improvements in performance.