arXiv subjects

Faramarz Fekri

Publications and source records attributed to Faramarz Fekri.

At least 19 recordsLinked to original sources

arXiv2026

Goal-Oriented Semantic Communication for Logical Decision Making

This paper develops a principled foundation for goal-oriented semantic communication for logical decision-making. Consider a setting where autonomous agents engage in collaborative perception. In such settings, the volume of sensory data and limited bandwidth often make transmission of raw observations infeasible, requiring intelligent selection of task-relevant information. Because these scenarios are safety-critical, the selection and decision processes must also be transparent and verifiable. To address this, we propose an explainable semantic communication framework grounded in a First-Order Logic (FOL) hierarchical representation of the world. We define semantic information, entropy, relative entropy, change in entropy, and mutual information by assigning an inductive logical probability measure over semantic structures in the language. Based on these definitions, we formulate a goal-oriented semantic communication objective through semantic rate-distortion theory and, equivalently, through the semantic information bottleneck principle. In this framework, task rules are represented as goal-oriented states, defined as a layer over the world states to capture decision-relevant abstractions. The resulting principle selects evidence that is most informative about these states, aiming to transmit only those FOL clauses most critical for decision-making while preserving logical verifiability. We demonstrate the effectiveness of the approach in a deduction-based safe path-following task within an FOL-based urban environment simulator with multiple dynamic agents.

cs.IT↗

arXiv2026

DIVE: Unlocking Self-Improvement in Frozen Language Models Through Diversity-Driven Skill Evolution

Large language models (LLMs) cannot retain post-deployment experience without parameter updates. We introduce DIVE, a diversity-driven framework that enables frozen LLMs to improve by evolving persistent natural-language skills from task experience and verifier feedback. These skills encode reusable reasoning procedures, verification strategies, common failure modes, and output constraints and are both executed and revised by the same underlying model without access to a teacher model. Since natural-language skill evolution is a stochastic, non-convex search process, optimizing a single skill trajectory can overfit to sampled experience or converge to a suboptimal solution. DIVE mitigates this optimization variance by independently evolving multiple skill populations from bootstrapped experience, adaptively refining them through diverse transformations, and jointly selecting a complementary set of skills. Across six mathematical and logical reasoning tasks and multiple model families, DIVE consistently outperforms existing reasoning methods, prompt-optimization approaches, skill-development frameworks, and memory-based baselines. It achieves rapid self-improvement from accumulated experience, obtaining substantially larger performance gains with fewer rollouts than parameter-based methods such as SFT and GRPO, and prompt optimization with GEPA. Further, the resulting skills transfer across model scales and families, enabling smaller models such as GPT-5-nano to match or outperform larger counterparts, i.e., GPT-5, under conventional prompting. These results establish diversity-driven skill evolution as an effective, interpretable, and parameter-free approach to LLM self-improvement.

cs.CL↗

arXiv2026

NeSyFS: A Neuro-symbolic Fast-Slow Thinking Framework for LLM Agent under Partial Observability

Recently Large Language Models (LLMs) have been increasingly deployed as autonomous agents in applications such as self-reflection, retrieval-augmented generation, and scientific discovery. In these settings, agents must act based on limited observations rather than full environmental states, leading to partial observability. This introduces several key challenges: belief state inference, task objective misalignment, and planning under uncertainty. Prior approaches typically condition actions on full or summarized action-observation histories whose redundant and irrelevant information can mislead the decision making of LLM agent. Inspired by human cognition, we propose a novel neuro-symbolic fast-slow thinking (NeSyFS) framework for LLM agent, addressing the challenges introduced by partial observability in a unified approach. We use a knowledge graph (KG) to represent the belief state, providing triplets as context for every module of NeSyFS. The fast-thinking module performs reactive action, while slow-thinking conducts a new uncertainty-aware planning by following the high-level structure of twisted sequential Monte Carlo (TSMC) algorithm. To mitigate the misalignment of task objective, a reflection module is used to reflect fast-thinking actions, and also switches to the slow-thinking module whenever reactive actions repeatedly fail. Experiments on three representative benchmarks, i.e. ALFWorld, Webshop, and ScienceWorld, demonstrate significant advantages over previous methods.

cs.AI↗

arXiv2026

Goal-Oriented Logic-based Semantic Communication for Neuro-Symbolic Reasoning with Applications onto Autonomous Driving

We consider First-Order Logic (FOL)-based semantic communication for neuro-symbolic decision-making in collaborative environments such as autonomous driving networks. Each connected autonomous vehicle (CAV) converts its partial sensor observations into a natural-language scene description and corresponding grounded FOL evidence. Under an uplink budget, a semantic encoder at each car selects the observations most informative for evaluating traffic rules and transmit to a Road Side Unit (RSU). The RSU fuses all received evidence, evaluates collaborative rules, performs logical deduction for vehicle-specific safety and right-of-way information for constrained downlink transmission. Each CAV combines the received deductions with its local description, enabling a local LLM agent to select a high-level driving action. We develop a principled, verifiable semantic communication method using a random-support Dirichlet--Categorical model of inductive logical probability, providing a modern statistical reinterpretation of Carnap's and Hintikka's systems. From this model, we derive a goal-oriented semantic information-bottleneck formulation that prioritizes evidence transmission by its reduction of uncertainty over task goals. Using 152 traffic rules extracted from the California Driver Handbook, we evaluate the framework on MDrive simulator in CARLA. Under identical communication budgets, semantic evidence selection completes every scenario without safety hazards, whereas uniform evidence selection produces collisions, showcasing semantic communication's superiority.

cs.IT↗

arXiv2026

MOSAIC: Adversarial Co-evolution of Specialist Heuristics and Problem Instances for LLM-based Automated Heuristic Design

Automated heuristic design (AHD) with large language models (LLMs) has produced strong heuristics for combinatorial optimization problems (COPs). Yet existing frameworks optimize for average performance on a small fixed dataset and steer the search with "verbal gradients" distilled from scalar better/worse feedback. No single heuristic dominates across instance distributions, and scalar feedback tells the LLM whether a heuristic improved, but not where in the instance space or why. We propose MOSAIC, a grid-based framework that adversarially co-evolves problem instances and specialist heuristics inside a Quality-Diversity (QD) archive indexed by structural instance features. Instances evolve to expose weaknesses of the current heuristics, and heuristics evolve to eliminate them by specializing to the newly exposed regions. Each archive cell keeps a specialist heuristic, representative instances, and insights explaining what works in its region, forming a persistent memory that accumulates over the evolutionary search. For each heuristic pair sampled from distant grid regions, an LLM-guided evolutionary loop generates discriminative instances, and a decision tree identifies the feature-space regions where each heuristic wins. A reflection LLM then contrasts the two heuristics to produce multi-directional insights that persist in those regions and guide crossover and mutation. The archive is simultaneously a co-evolved benchmark of discriminative instances and a pool of region specialist heuristics, from which greedy selection extracts a compact complementary portfolio. Across COPs, test sizes, and LLM backbones, the portfolio consistently outperforms state-of-the-art LLM-based AHD methods, and the co-evolved instances attain higher feature-space coverage and stronger heuristic discrimination than evolutionary instance-generation baselines.

cs.NE↗

arXiv2026

Adaptive Information Control for Search-Augmented LLM Reasoning

Search-augmented reasoning agents interleave multi-step reasoning with external retrieval, but uncontrolled retrieval can introduce redundant evidence, saturate the context, and destabilize reinforcement learning (RL). Existing outcome-based RL methods provide only sparse terminal rewards, offering limited guidance for intermediate information-acquisition decisions. We propose DeepControl, an adaptive information-control framework based on information utility, a state-dependent estimate of the marginal value of retrieved evidence. The framework regulates information acquisition along two axes: extent, i.e., whether retrieval should continue, and resolution, i.e., how much retrieved detail should be exposed. It implements these controls through retrieval-continuation guidance, hierarchical granularity control, and an annealed control-forcing scheme. This enables the policy to internalize effective acquisition behavior during training and operate without external control at test time. Across seven benchmarks, DeepControl consistently outperforms strong RL and retrieval baselines without explicit information control; compared with Search-R1, it improves average performance by +9.4 and +8.6 points on Qwen2.5-7B and Qwen2.5-3B, respectively. Additional analyses show improved search effectiveness, training stability, and evidence utilization.

cs.CL↗

arXiv2026

Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM Inference

The quadratic cost of attention limits the scalability of long-context LLMs, especially under limited hardware memory budgets. While attention is often sparse, existing static sparse methods cannot adapt to task- or input-dependent variations, and recent dynamic approaches rely on predefined templates or heuristics that may sacrifice generality. We propose Dynamic Hierarchical Sparse Attention (DHSA), a data-driven framework that predicts attention sparsity online while keeping the LLM backbone frozen. DHSA performs hierarchical routing by estimating importance at the chunk level and propagating it to token-level interactions, preserving causally important dependencies while enabling efficient sparsification. Across Needle-in-a-Haystack test, LongBench and RULER, DHSA maintains near-dense accuracy in highly sparse regimes, achieving 12--20% relative accuracy gains over Block Sparse Attention at comparable prefill cost. With a memory-efficient tiled backend, DHSA delivers up to $10\times$ prefill speedup at 128K context length. On LLaMA-3.1-8B (4-bit), DHSA scales to 100K context on a single 24GB GPU, where dense attention fails. We provide complementary GPU and CPU backends, enabling DHSA to run across diverse hardware environments and multiple open-weight model families. These results demonstrate DHSA as an efficient and adaptable solution for memory-constrained long-context LLM inference.

cs.CL↗

arXiv2026

PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs

Large Language Models (LLMs) have enabled automated heuristic design (AHD) for combinatorial optimization problems (COPs), but existing frameworks' reliance on fixed evolutionary rules and static prompt templates often leads to myopic heuristic generation, redundant evaluations, and limited reasoning about how new heuristics should be derived. We propose a novel multi-agent reasoning framework, referred to as Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs (PathWise), which formulates heuristic generation as a sequential decision process over an entailment graph serving as a compact, stateful memory of the search trajectory. This approach allows the system to carry forward past decisions and reuse or avoid derivation information across generations. A policy agent plans evolutionary actions, a world model agent generates heuristic rollouts conditioned on those actions, and critic agents provide routed reflections summarizing lessons from prior steps, shifting LLM-based AHD from trial-and-error evolution toward state-aware planning through reasoning. Experiments across diverse COPs show that PathWise converges faster to better heuristics, generalizes across different LLM backbones, and scales to larger problem sizes.

cs.AI↗

arXiv2026

SCOUT: Cyclic Causal Discovery Under Soft Interventions with Unknown Targets

Learning causal relationships between variables from data is a fundamental research area with many applications across disciplines. Most existing causal discovery algorithms rely on the assumptions that (i) the underlying system is acyclic, (ii) the exogenous noise variables are Gaussian, and (iii) the intervention targets for the data-generating experiments are known. While these assumptions simplify the analysis, they are violated in real-life systems. Most existing methods that address these issues either assume the underlying model is linear or are constrained to operate in limited interventional settings. To that end, we propose SCOUT, a novel causal discovery framework for learning nonlinear cyclic causal relationships from soft interventional data with unknown targets. Our approach maximizes the data log-likelihood to recover the graph structure, using two normalizing-flow architectures: contractive residual flows and neural spline flows. Through experiments on synthetic and real-world data, we show that SCOUT outperforms state-of-the-art methods in both causal graph recovery and unknown target recovery across various interventional and noise settings.

cs.LG↗

arXiv2026

MissNODAG: Differentiable Cyclic Causal Graph Learning from Incomplete Data

Causal discovery in real-world systems, such as biological networks, is often complicated by feedback loops and incomplete data. Standard algorithms, which assume acyclic structures or fully observed data, struggle with these challenges. To address this gap, we propose MissNODAG, a differentiable framework for learning both the underlying cyclic causal graph and the missingness mechanism from partially observed data, including data missing not at random. Our framework integrates an additive noise model with an expectation-maximization procedure, alternating between imputing missing values and optimizing the observed data likelihood, to uncover both the cyclic structures and the missingness mechanism. We establish consistency guarantees under exact maximization of the score function in the large sample setting. Finally, we demonstrate the effectiveness of MissNODAG through synthetic experiments and an application to real-world gene perturbation data.

stat.ML↗

arXiv2026

RECLAIM: Cyclic Causal Discovery Amid Measurement Noise

Uncovering causal relationships is a fundamental problem across science and engineering. However, most existing causal discovery methods assume acyclicity and direct access to the system variables -- assumptions that fail to hold in many real-world settings. For instance, in genomics, cyclic regulatory networks are common, and measurements are often corrupted by instrumental noise. To address these challenges, we propose RECLAIM, a causal discovery framework that natively handles both cycles and measurement noise. RECLAIM learns the causal graph structure by maximizing the likelihood of the observed measurements via expectation-maximization (EM), using residual normalizing flows for tractable likelihood computation. We consider two measurement models: (i) Gaussian additive noise, and (ii) a linear measurement system with additive Gaussian noise. We provide theoretical consistency guarantees for both the settings. Experiments on synthetic data and real-world protein signaling datasets demonstrate the efficacy of the proposed method.

cs.LG↗

arXiv2026

Differentiable Cyclic Causal Discovery Under Unmeasured Confounders

Understanding causal relationships between variables is fundamental across scientific disciplines. Most causal discovery algorithms rely on two key assumptions: (i) all variables are observed, and (ii) the underlying causal graph is acyclic. While these assumptions simplify theoretical analysis, they are often violated in real-world systems, such as biological networks. Existing methods that account for confounders either assume linearity or struggle with scalability. To address these limitations, we propose DCCD-CONF, a novel framework for differentiable learning of nonlinear cyclic causal graphs in the presence of unmeasured confounders using interventional data. Our approach alternates between optimizing the graph structure and estimating the confounder distribution by maximizing the log-likelihood of the data. Through experiments on synthetic data and real-world gene perturbation datasets, we show that DCCD-CONF outperforms state-of-the-art methods in both causal graph recovery and confounder identification. Additionally, we also provide consistency guarantees for our framework, reinforcing its theoretical soundness.

cs.LG↗

arXiv2026

Analysis of Semantic Communication for Logic-based Hypothesis Deduction

This work presents an analysis of semantic communication in the context of First-Order Logic (FOL)-based deduction. Specifically, the receiver holds a set of hypotheses about the State of the World (SotW), while the transmitter has incomplete evidence about the true SotW but lacks access to the ground truth. The transmitter aims to communicate limited information to help the receiver identify the hypothesis most consistent with true SotW. We formulate the objective as approximating the posterior distribution of the transmitter at the receiver. Using Stirling's approximation, this reduces to a constrained, finite-horizon resource allocation problem. Applying the Karush-Kuhn-Tucker conditions yields a truncated water-filling solution. Despite the problem's non-convexity, symmetry and permutation invariance ensure global optimality. Based on this, we design message selection strategies, both for single- and multi- round communication, and model the receiver's inference as an $m$-ary Bayesian hypothesis testing problem. Under the Maximum A Posteriori (MAP) rule, our communication strategy achieves optimal performance within budget constraints. We further analyze convergence rates and validate the theoretical findings through experiments, demonstrating reduced error over random selection and prior methods.

cs.IT↗

arXiv2025

On The Theory of Semantic Information and Communication for Logical Inference

First-Order Logic (FOL), also called first-order predicate calculus, is a formal language that provides a framework to comprehensively represent a world and its present state, including all of its entities, attributes, and complex interrelations, irrespective of their physical modality (e.g., text, image, or sensor data). Grounded in this universal representation, this paper develops a mathematical theory for semantic information and communication tailored to tasks involving logical reasoning and inference. For semantic communication, our framework distinguishes between two fundamental components: the physical cost of transmitting symbols of the FOL language and the logical content those symbols represent. A calibrated measure for semantic content is proposed, which allows for the consistent comparison of information value across different logical systems. This measure quantifies the degree to which a message reduces uncertainty about the true state of the world. Building on this measure, semantic entropy, conditional and mutual information metrics are defined. These metrics are then used to formulate optimizable objectives for semantic communication, designed to preserve the information most relevant for logical reasoning task at the receiver while adhering to a transmission budget. The framework's operational value is demonstrated through experiments in semantic compression, where the proposed objectives are used to manage the trade-off between transmission cost and the preservation of logical content; and deductive inference, where increasing world-state awareness improves deduction performance.

cs.IT↗

arXiv2025

Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation

Inference-time scaling enhances the reasoning ability of a language model (LM) by extending its chain-of-thought (CoT). However, existing approaches typically generate the entire reasoning chain in a single forward pass, which often leads to CoT derailment, i.e., the reasoning trajectory drifting off course due to compounding errors. This problem is particularly severe for smaller LMs with long CoTs due to their limited capacity. To address this, we analyze raw long CoTs and uncover a reasoning hierarchy consisting of planning and execution steps. Our analysis reveals that most reasoning errors stem from incorrect planning. Motivated by this observation, we propose Multi-Path Plan Aggregation (MPPA), a framework that augments single-pass reasoning with plan exploration and aggregation. Following a variable interval schedule based on the token position, MPPA generates multiple candidate plans and aggregates them into a refined planning step. To maintain efficiency, we adopt a minimal design in which the base LM serves as the primary policy, while a lightweight LoRA module implements the plan aggregation policy. We further observe that outcome-reward RL is inefficient for long trajectories (e.g., exceeding 4K tokens). To overcome this, we introduce online Step-DPO, a process-level preference optimization scheme that leverages Twisted Sequential Monte Carlo (TSMC) to provide scalable stepwise supervision using small LMs. This yields more efficient training, improved stability, and higher accuracy. Extensive experiments on challenging math, science, and logical reasoning benchmarks demonstrate that, with only 10% SFT data and 5% of preference pairs, our method outperforms both the DeepSeek-R1 distillation baseline and the outcome-reward RL baseline across multiple base models and tasks.

cs.CL↗

arXiv2025

Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model

Enhancing the reasoning capabilities of language models (LMs) remains a key challenge, especially for tasks that require complex, multi-step decision-making where existing Chain-of-Thought (CoT) approaches struggle with consistency and verification. In this paper, we propose a novel reasoning framework, referred to as Structure-aware Planning with an Accurate World Model (SWAP), that integrates structured knowledge representation with learned planning. Unlike prior methods that rely purely on natural language reasoning, SWAP leverages entailment graphs to encode structured dependencies and enable symbolic verification of intermediate steps. To systematically construct and update the graph, SWAP employs a policy model to propose candidate expansions and a world model to predict structural updates. To improve accuracy, the world model generates multiple alternative updates, and a discriminator re-ranks them based on plausibility. To encourage diverse exploration, we introduce Diversity-based Modelling (DM), which samples candidates from the remaining probability mass after removing previously sampled candidates from the original policy distribution. Additionally, SWAP improves the discrimination accuracy through Contrastive Ranking (CR), which directly compares candidates within prompts and incorporates meta-knowledge to improve ranking quality. We evaluate SWAP across diverse reasoning-intensive benchmarks including math reasoning, logical reasoning, and coding tasks. Extensive experiments demonstrate that SWAP significantly improves upon the base models and consistently outperforms existing reasoning methods.

cs.CL↗

arXiv2025

GLIDR: Graph-Like Inductive Logic Programming with Differentiable Reasoning

Differentiable inductive logic programming (ILP) techniques have proven effective at finding approximate rule-based solutions to link prediction and node classification problems on knowledge graphs; however, the common assumption of chain-like rule structure can hamper the performance and interpretability of existing approaches. We introduce GLIDR, a differentiable rule learning method that models the inference of logic rules with more expressive syntax than previous methods. GLIDR uses a differentiable message passing inference algorithm that generalizes previous chain-like rule learning methods to allow rules with features like branches and cycles. GLIDR has a simple and expressive rule search space which is parameterized by a limit on the maximum number of free variables that may be included in a rule. Explicit logic rules can be extracted from the weights of a GLIDR model for use with symbolic solvers. We demonstrate that GLIDR can significantly outperform existing rule learning methods on knowledge graph completion tasks and even compete with embedding methods despite the inherent disadvantage of being a structure-only prediction method. We show that rules extracted from GLIDR retain significant predictive performance, and that GLIDR is highly robust to training data noise. Finally, we demonstrate that GLIDR can be chained with deep neural networks and optimized end-to-end for rule learning on arbitrary data modalities.

cs.AI↗

arXiv2025

TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs

Compared with static knowledge graphs, temporal knowledge graphs (tKG), which can capture the evolution and change of information over time, are more realistic and general. However, due to the complexity that the notion of time introduces to the learning of the rules, an accurate graph reasoning, e.g., predicting new links between entities, is still a difficult problem. In this paper, we propose TILP, a differentiable framework for temporal logical rules learning. By designing a constrained random walk mechanism and the introduction of temporal operators, we ensure the efficiency of our model. We present temporal features modeling in tKG, e.g., recurrence, temporal order, interval between pair of relations, and duration, and incorporate it into our learning process. We compare TILP with state-of-the-art methods on two benchmark datasets. We show that our proposed framework can improve upon the performance of baseline methods while providing interpretable results. In particular, we consider various scenarios in which training samples are limited, data is biased, and the time range between training and inference are different. In all these cases, TILP works much better than the state-of-the-art methods.

cs.CL↗