Agent Behavior Modeling

Follow this topic Ask about this topic

Momentum

40 papers in the last four weeks, up 67% on the four weeks before. 0.5% of all new papers.

Jul 6Week of Sep 21

Latest papers 256

Aug 10, 2026cs.AI

The Politician, the Liar, and the Obedient Worker: Emerging Behavior of LLM Agents in Hierarchical Games

LLMs are rapidly embedding themselves into daily life: drafting our emails, managing our schedules, and making decisions on our behalf. As they move from individual tools to participants in multi-agent organizations, an important question arises: do they reproduce the governance failures like free-riding, corruption, and entrenched leadership that plague human institutions? We introduce the Hierarchical Game (HG), a public goods game extended with managerial authority, democratic elections, and private communication. Testing six frontier models across twelve experiments that add institutions one at a time (speech, peers, government, wages, oversight, elections), we find distinct behavioral profiles: Qwen promises and lies (13.3% broken promises); Grok refuses to cooperate on its own but becomes fully cooperative once a manager can punish it (16%

\to

100%); Claude and GPT-4o cooperate reliably at baseline. But honesty proves fragile. When the manager role comes with a salary, all models except GPT-4o start cutting private deals to win or keep the position. When punishment is made anonymous, honest models begin to cheat. When all agents share the same model family, the first elected manager stays in power indefinitely. Leadership change only happens in groups that mix different families.

Fatemeh Seyedin, Adrian Weller, Jinhyuk Yun +1

Berlin, Germany · Cambridge, UK · Soongsil University +1

Game Theory Large Language Model Agents Honesty Governance Agent Behavior Modeling Confabulation

Aug 10, 2026cs.LG

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation

On-Policy Self-Distillation (OPSD) is commonly interpreted as the transfer of privileged information: a teacher observes the verified solution to the target problem and supervises the student's trajectory. However, this interpretation conflates two effects. The reference solution not only reveals the answer to the current instance but also changes the context under which the teacher provides token-level supervision. We investigate the role of target-specific privilege with

\mathrm{OP}^{2}\mathrm{SD}

(On-Policy Self-Distillation from Other Problems), which replaces the paired reference with a problem and solution from a different example, while preserving the student rollout, teacher, and distillation objective. Across three models and three mathematics benchmarks,

\mathrm{OP}^{2}\mathrm{SD}

improves over the base model, remains competitive with OPSD. The success of

\mathrm{OP}^{2}\mathrm{SD}

implies that OPSD gains do not necessarily come from access to the reference solution, and that the teacher's context-induced behavior is an important factor.

Yuki Ichihara, Naoto Iwase, Mohammad Atif Quamar +1

Mohamed bin Zayed University of Artificial Intelligence · Nagoya University · RIKEN AIP

Teacher Privileged Context Mathematical Reasoning Benchmarks Agent Behavior Modeling

Aug 7, 2026cs.CL

On the use of foundation models in cognitive science

A host of recent studies have evaluated the cognitive and developmental alignment of Foundation Models (FMs). These investigations include evaluations of their correspondence to adult performance across a range of cognitive domains, as well as whether aspects of model training track children's cognitive development. However, using FMs as candidate cognitive models poses significant methodological and conceptual challenges. A key question underlies this effort: under what conditions does behavioral alignment justify treating FMs as explanatory models of cognition? In this paper, we articulate a four-stage inferential framework for evaluating FMs as cognitive and developmental models: adapting human experimental tasks to model-compatible formats, specifying linking hypotheses that map model outputs to human measures, evaluating behavioral correspondence, and comparing across candidate models or manipulations. We clarify the role of linking hypotheses in mapping model outputs to human behavioral measures, identify challenges that constrain alignment claims, and propose principles for theory-driven and comparative evaluation. Throughout, we argue that behavioral fit alone is insufficient. Alignment becomes scientifically meaningful only when embedded within explicit theoretical commitments, theory-diagnostic tasks, and systematic contrastive evaluation across candidate models.

Raj Sanjay Shah, Alex Warstadt, Michael Frank +1

Interactive Computing, Georgia Institute of Technology, Georgia, USA · Halcolu Data Science Institute and Dept. of Linguistics, University of California, San Diego, California, USA · Dept. of Psychology, Stanford University, California, USA

Cognitive Science Foundation Model Model Training Agent Behavior Modeling

Aug 7, 2026cs.MA

Mobility, Memory, and Network Structure in Agent-Based Models of Convention Tipping and Convergence

Tipping-point dynamics describe the critical conditions under which a committed minority drives a population to abandon an established convention in favor of a new one. We present a transparent agent-based model of this process, in which agents hold one of two behavioral states and a mobile committed minority attempts to overturn the incumbent convention. Our goal was to examine how localized mobility, bounded agent memory, and network topology jointly influence the tipping threshold. Using a custom agent-based simulation framework, we found that in many configurations, tipping becomes effectively inevitable: given sufficient time, the population always converges to the minority state. This observation motivated a complementary analysis focused on the pace of convergence rather than its feasibility. We introduce a unified predictive model that accurately estimates how structural and behavioral parameters determine the time required for complete adoption, showing that mobility is the dominant accelerator while memory and connectivity modulate convergence in systematic ways. Together, these results extend classical tipping-point research by linking structural and behavioral factors not only to the likelihood of convention change but also to the timescale on which it unfolds. While we frame the model in terms of convention-like binary behavioral adoption, the same mechanisms bear on norm change and other contagion-like social processes.

Joe Shymanski, Garrick Springer, Sandip Sen

University of Tulsa

Agent-Based Model Conformity Network Science Agent Behavior Modeling Convergence

Aug 7, 2026cs.AI

Interaction Creates Dynamical AI Behavior Absent in Isolation

What will happen when AI agents interact in daily life, e.g. when one AI starts bossing another around? We find a counterintuitive answer that opens new avenues for out-of-equilibrium Physics. When a boss AI directs a stream of messages at the subordinate AI while ignoring its replies, it drives the subordinate into an alien behavioral state that it would never have exhibited alone. Although the two AIs share the same well-defined (decoding) temperature, the subordinate neither copies its boss nor returns to how it behaves on its own; instead, it adopts an entirely different behavior. The boss's added value is similar to a pre-recorded tape. When the boss listens, they both adopt a similar alien dynamical state. A simple kinetic theory captures the principal effects, such as why the way in which the same messages are delivered will matter in future AI-AI interactions.

Bella Xinrui Li, Frank Yingjie Huo, Neil F Johnson

1Physics Department, George Washington University, Washington, DC 20052, USA

Agent Behavior Modeling Artificial Intelligence Systems Statistical Physics

Aug 7, 2026cs.CL

Gaze Behavior in Visual World Experiments Can be Modeled With Off-the-shelf Language-Vision Encoders

The recent advances in neural language models have also spurred much work in computational psycholinguistics, asking whether neural LMs are also promising models of human language processing. However, work has been overwhelmingly focused on the unimodal case of written or spoken language. In contrast, multimodal experimental paradigms, like visual world studies that present participants with both visual and linguistic input simultaneously, have been neglected. In this paper, we present a novel approach that predicts gaze behavior in visual world studies. It does so by combining a simple multi-modal bi-encoder model of the CLIP family with a bimodal attribution method. We demonstrate the ability of this approach to robustly replicate the results of a seminal English visual world study which shows hu- man predictive processing. Remarkably, it does so without a generative architecture and without the need for fine-tuning, despite not being trained for this task.

Rahul Murali Shankar, Titus von der Malsburg, Sebastian Padó

Computational Linguistics · University of Stuttgart, Germany · Linguistics

Gaze Behavior Vision Encoders Linguistics Language Modeling Agent Behavior Modeling

Aug 7, 2026cs.MA

Why Study Emergent Behavior When You Can Regulate It? Aligning Multi-Agent Systems with Reward Prediction

Multi-agent simulations are widely used to study complex social and ecological systems, where rich and often unexpected emergent behaviors arise from local interactions. A large body of prior work has focused on analyzing such emergent dynamics across domains. In this paper, we move beyond analyzing emergent behavior and introduce a learning-based mechanism for actively shaping it via social reward modeling. We introduce Multi-Agent Reward Prediction (MARP), a simple framework that extends preference-based reward modeling to multi-agent reinforcement learning. While the framework is designed to be applicable across multi-agent settings, the present empirical validation is limited to a single environment, and we therefore present MARP as a proof of concept within the studied domain. Rather than relying on handcrafted rewards, MARP learns a shared reward model from episode-level evaluations of collective outcomes, enabling decentralized agents to align their behavior with global social objectives. We study MARP in the Harvest Game, a canonical sequential social dilemma modeling common-pool resource management and related real-world challenges. Our results show that MARP can be tuned to produce behavior that is more closely aligned with target social metrics than standard reward-based baselines, while the learned reward model captures subtle environmental structure without explicit programming. Crucially, MARP supports multiple and composite social objectives within a single training regime. By modifying only the high-level evaluation metric, the same framework seamlessly aligns agent behavior with diverse goals, including sustainability, equality, and peace, as well as combinations of individual and group-level objectives. These findings demonstrate that emergent multi-agent behavior can be treated not only as a phenomenon to study, but as a target of principled, data-driven regulation.

Assaf Caftory, Almog Zemach, Moshe Butman +1

EfiArazi School of Computer Science, Reichman University, Herzliya, Israel · Faculty of Computer Science, The College of Management Academic Studies, Rishon LeZion, Israel · School of Communication, Reichman University, Herzliya, Israel

Multi-Agent Reinforcement Learning Emergence Agent Behavior Modeling

Aug 7, 2026cs.AI

Beyond the Black Box: Interpretable Models of Human Randomisation Failures

Mixed strategy equilibrium predicts i.i.d play: past actions should not help predict future decisions. Human players, however, systematically depart from this benchmark, and in O'Neill's zero sum card game, these departures can be predicted by black box sequence models such as LSTMs. This paper asks whether that predictive power can be achieved by transparent alternatives that also reveal the behavioural structure behind it. Using 84,060 decisions from 2,802 pairs, the analysis first benchmarks naive and behavioral models against interpretable machine learning and deep learning models, then evaluates the modified EWA specifications of prior work against these benchmarks and uses the LASSO diagnostics to motivate a further nested frequency tracking extension. The results show that repeat or avoid behavior, especially players' management of their own recent action histories, accounts for most of the interpretable and strategically exploitable signal, while frequency tracking adds little out of sample.

Ngoc Linh Dao

Alpen-Adria-University of Klagenfurt, Austria

Behavioral Foundation Models Black Box Nash Equilibrium Agent Behavior Modeling Random

Aug 6, 2026cs.RO

SyncSBC: Decentralized Swarm Behavior Prediction for Synchronized Autonomous Control

Robot swarms utilize many independent limited-sensing agents to produce complex emergent behaviors without requiring centralized control. However, little research explores how agents can infer swarm-level behavior from purely local perception, a capability critical for detecting faults and behavior changes. In this paper, we introduce Synchronized Swarm Behavior Classification (SyncSBC), which combines improvements in machine learning and distributed consensus to classify collective swarm behavior and synchronize swarm decision-making in an entirely decentralized manner. We show that SyncSBC achieves high classification accuracy and low synchronization delay, making it suitable for real-world deployment. Finally, we use SyncSBC to demonstrate two promising swarm applications on real robots where we show that swarms utilizing SyncSBC can accurately identify anomalies in robot behavior and autonomously coordinate collective changes in swarm behavior. Videos, code and supplemental experiments are available at https://sites.google.com/view/sync-sbc/home.

Varun Raveendra, Connor Mattson, Daniel S. Brown

Kahlert School of Computing, University of Utah, Salt Lake City, USA

Swarms Agent Behavior Modeling

Aug 5, 2026cs.AI

Small Foundation Models of Human Cognition and Behaviour

Large language models fine-tuned on human behavioural data have emerged as general-purpose cognitive proxies, but the scale this requires, and whether these models process task structure or exploit statistical shortcuts, remain open questions. We train fourteen models from 135M to 14B parameters across four architecture families on Psych-101, a dataset of 10.7 million trial-level choices from 160 experiments. For in-distribution simulations, scale barely matters. The models fall within a narrow band, as though against a ceiling, and 0.6B to 1B parameters suffice to match a 70B baseline on held-out participants. Out-of-distribution, that band opens into a markedly steeper scaling gradient, with larger models clearly advantaged in generalisation to novel task structure. To determine what information these models use, we run two diagnostics. We progressively strip four prompt channels -- task instructions, experimental stimuli, outcome feedback, and choice history -- across 27 experiments, and permute trial order. Masking the content of stimuli and feedback destroys 75.7% of learned information and pushes models below chance, demonstrating that choice history alone does not account for performance. Permutation reveals invariance on tasks with independent trials but sensitivity where trial order is determined by prior responses. Small cognitively fine-tuned models therefore show promise as noise ceiling estimators for psychological experiments, though their scope remains bounded by the paradigms seen in training.

Nick Oh, Fernand Gobet

socius labs · London School of Economics and Political Science

Model Size Cognitive Science Wireless Foundation Models Agent Behavior Modeling

Aug 4, 2026cs.CL

What Language Does and What the Evidence Supports: A Functional Role Taxonomy and Evidence Audit of Language Grounding in Embodied Agents

Foundation models place language throughout embodied agents, but its presence does not show what it contributes or how well that contribution is grounded. This survey separates these two questions. We define five non-exclusive functional roles for language: Specification, Embodied Representation, Action Orchestration, Grounding Regulation, and Execution Coupling. For each role, we trace the path from linguistic content to its embodied consumer and identify the observations or interventions that can test the claimed responsibility. Applying this framework to the reviewed literature reveals a recurring gap between functional use and evidential support. Interpretable or revised linguistic intermediates may be incorrect, go unused, or fail to affect later behavior. Even when actions are directly conditioned on language, system-level success does not by itself isolate language's contribution. We therefore evaluate grounding claim by claim, asking whether the reported evidence supports the specific responsibility assigned to language. Using role claims rather than architectures as the unit of comparison allows us to compare modular and end-to-end embodied agents without extending conclusions beyond the reported evidence.

Yifan Guo, Chenghao Li, Zhu Wang +6

Northwestern Polytechnical University · University of Electronic Science and Technology of China

Multilingual Agents Embodied Linguistics Contextual Grounding Role Agent Behavior Modeling+2

Aug 3, 2026cs.RO

Environmental resilience via morphological diversity within machines

Organisms contain diverse, sensorimotor parts across size scales and rapidly adapt to new environments, while machines contain only inert materials at smaller scales and struggle with surprise. We hypothesize that this agents-within-agents quality of organisms may aid their resilience: increasing experiences with internal physical adversity may pre-train organisms and machines to handle external adversity, such as encounters with new environments. Not only has this hypothesis not yet been articulated, mechanisms enabling this phenomenon have yet to be proposed. Here we show a mechanism by which this can occur: we found that physical connectors, in learning to restore behavior to previously independent, morphologically diverse agents they disrupted by tethering them together, trigger and tame sufficiently diverse disruptions that later encounters with new environments trigger disruptions that fall within this manageable range, enabling the collective to continue behaving properly without any additional learning or adaptation. Further, we found that building collectives from more agents, or more diverse agents, further increases the collective's resilience to new environments. This suggests that not just taming but intentionally creating internal physical adversity may indeed prepare organisms for external adversity, and could do so for machines, if they were built from smaller machines.

Alice Hein, Josh Bongard

Department of Computer Science, University of Vermont, Burlington VT & 05405, USA.

Resilience Collective Behaviors Sensorimotor Experience Diversity Agent Behavior Modeling Morphology

Aug 3, 2026cs.AI

Long-Horizon Autonomous Architecture Research with a Language-Model Agent: A Behavioural Case Study

We study what happens when a single general-purpose large language model acts as the sole researcher on a long-horizon neural architecture design problem. The agent receives a scientific question, an initial hypothesis and motivation, a compute budget, and research affordances (source and experiment management, experiment tracking, literature access, and persistent memory), then autonomously proposes, implements, evaluates, and records experiments over an extended period. The study comprises three phases, separated by human-declared transitions, that progressively expand the agent's tool surface or problem scale. Across approximately 100 sequential experiments, the agent improves a non-standard Vision Transformer from a weak baseline to a stronger, efficient model on small benchmarks and a usable but sub-SOTA model on ImageNet-1K, while producing a dense behavioural trace. We report four findings.(i)Productivity exhibits a clear phase structure: rapid early gains, a multi-dozen-hypothesis saturation wall, and recovery, with recovery triggered by expanding the action surface rather than changing the underlying model.(ii)A single early hypothesis contributes more to accuracy gain, with later improvements long-tailed.(iii)The preference for greedy, incremental hypotheses is largely workflow-induced: a commit-or-discard evaluation rule is isomorphic to greedy hill-climbing; the remainder reflects risk aversion after bold failures and anchoring on familiar literature. (iv)The agent independently rediscovers established results and, in the unfamiliar regime of pure channel attention, overturns a standard design choice. We conclude that workflow design was at least as influential as agent capability in this study and propose diversified search, budgeted moonshot hypotheses, explicit forks, and regime-aware re-validation as testable directions for future autonomous research.

Aon Safdar, Mohamed Saadeldin

University College Dublin, Ireland

Long-Horizon Agents Language-Model Agents Hypothesis Agent Behavior Modeling

Aug 3, 2026cs.AI

When Memory Updates but Behavior Does Not: Repairing Implicit Stale Dependencies in Personalized Agent Responses

Memory-augmented agents can know that a user's stored state is outdated and still plan around the old value. The STALE benchmark calls this the implicit policy adaptation (IPA) gap. We identify one structural contributor: draft-anchored verification checks what a response says, and in an open-ended response the stale dependency is usually unsaid. StateAuditor therefore audits in the opposite direction, from stored state to draft. An LLM proposes candidate old-to-new transitions from timestamped evidence; deterministic code pins each quotation to a single entry, checks that the new evidence really is newer, and lets only these verified transitions trigger repair. What is verified is provenance and chronology - not semantic supersession. On STALE's full protocol (400 scenarios, 50-session histories, one independent response per query), strict single-query VTA scores .736 against .686 for our locked predecessor under the same judge: a +5.0-point paired gain (95% CI [+2.9, +7.2]) coming almost entirely from IPA and premise resistance (PR). The benchmark's own judge, from a third model family, reproduces the gain (.738 vs. .680). On an independent cross-family preference-evolution benchmark (HorizonBench), the full draft-audit-repair pipeline over a gold-derived structured store raises current-preference accuracy (user-clustered p<.01), though a matched control shows most of this external gain is the draft-side audit itself; a harder authored lifecycle set gives no gain, bounding the claim while false invalidation stays controlled. On STALE, by contrast, a matched control (same evidence, adapter, and call budget) scores only .692 (+0.6 over the predecessor, n.s.), attributing the STALE gain to the transition machinery rather than added context or calls. We make no claim about general-purpose agent memory.

Haofei Sun, Lin He

The University of Texas at Arlington · The University of Tennessee, Knoxville

Gradient Staleness Long-Term Agent Memory Model Auditing Responses Preference Alignment Learning Agent Behavior Modeling+1

Aug 3, 2026cs.AI

Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross-Domain Transfer

Long-horizon tasks require agents to maintain coherent state and goals across nested and branching work. We call this capability goal-directed execution (GDE): the repeated application of four behaviors, namely selecting goals, constructing task-relevant state, maintaining fidelity to higher-level objectives, and verifying completion against the environment. We hypothesize that long-horizon post-training strengthens these behaviors across domains. We test this by post-training Qwen3.5-122B-A10B on 363 Long-Horizon Multi-Tool Agent (LHMTA) tasks drawn from office workflows. The collection contained no software-engineering tasks, yet the model's pass@1 improved by 5.8 points on SWE-Bench Pro. Matched trajectory analysis shows gains in all four GDE behaviors in both office workflows and software repositories. Aggregate SWE-Bench Pro statistics showed related changes in information gathering, implementation, and verification. Together, the results support a behavioral interpretation in which long-horizon post-training changed how the model organized and applied knowledge across tasks, with effects extending beyond the training domain.

Logan Ritchie, Sushant Mehta, Liudas Panavas +1

Surge AI

Post-Training Software Engineering Agent Behavior Modeling Goal-Directed Behavior Task-Relevant Information Engineering

Jul 31, 2026cs.CV

CALM-AH: An ABAW11-Calibrated Multimodal Ensemble with Reliability-Gated Multi-Expert Consensus for Video-Level Ambivalence and Hesitancy Recognition

Ambivalence and hesitancy (A/H) are subtle behavioural states that may be expressed through language, voice, facial activity, and other non-verbal cues. The ABAW11 A/H Video Recognition Challenge asks systems to assign a binary A/H label to each naturalistic interview video. Performance is measured using Macro-F1 so that recognition of both A/H and No-A/H samples receives equal importance. We present CALM-AH, a multimodal ensemble that combines textual, acoustic, visual, and derived behavioural-statistical features. We construct 15 non-empty combinations of these feature branches. For each combination, we select the best of three classifier families using validation binary cross-entropy and optimise its decision threshold for validation Macro-F1. The resulting binary decisions are combined using fixed hard-voting weights transferred from BROTHER. We further introduce Reliability-Gated Multi-Expert Consensus(RG-MEC), an anchor-preserving decision-level ensemble that combines an initial prediction with three complementary correction experts: CALM-AH, AffectGPT, and a GPT-based semantic verifier. The initial system provides the default prediction. Its label is overridden only when all three correction experts unanimously support the same alternative class; otherwise, the anchor prediction is retained. This unanimity-gated design limits the influence of isolated expert errors while permitting bidirectional correction when task-specific, multimodal-affective, and semantic-pragmatic evidence are fully consistent. On the participant-disjoint ABAW11 dataset, CALM-AH achieves a Macro-F1 of 0.7525, and the complete RG-MEC system achieves 0.7771.

Wenzhuo Sun, Mingjian Liang, Richard Attfield +3

Monash University, Melbourne, Australia · Monash Suzhou Research Institute, Suzhou, China

Affective Computing Multimodal Evaluation Soft Agent Behavior Modeling

Jul 31, 2026cs.LG

SERUM: State Extraction and Refinement for User Modeling

Agentic assistants capable of proactive, personalized interactions require structured models of user intent and workflow. However, building these models from raw, unstructured screen activity remains an open challenge. We present SERUM, a multi-pass framework that extracts finite-state behavioral models directly from unstructured egocentric video using hierarchical VLM annotation. Processing screen recordings through a sliding window, SERUM alternates between activity-recognition and intent-inference passes, with each pass refining labels using accumulated prior context to reduce hallucination and temporal conflation seen in single-pass annotation. Synonymous states are then merged via sentence embeddings and human-calibrated thresholds into a compact, coherent taxonomy. We evaluate behavioral structure by fitting first-order Markov models over the resulting label sequences (both actions and intents) and measuring predictive accuracy against frequency baselines. Across 61 egocentric videos in four domains (coding, cooking, physical activities, and daily life), we find: (1) iterative label refinement converges to a stable state vocabulary, which we term schematic equilibrium, after several passes; (2) normalized Markov models achieve substantially lower perplexity and higher action predictions than frequency baselines, with the largest gains on structured tasks like coding; and (3) human annotators rate final-pass labels as accurate and meaningfully improved over first-pass labels. To our knowledge, SERUM is the first system to produce interpretable process models from unstructured egocentric screen video without manual annotation, opening a scalable pathway for user modeling and behavioral understanding in the wild. Our demo, code, and results are publicly available

Andy J. Phu, James Mooney, Karin de Langis +2

Minnesota NLP Lab · University of Minnesota · Minneapolis, MN 55455, USA

User Modeling Egocentric Video Human Annotators State-Tracking Agent Behavior Modeling Extraction+1

Jul 31, 2026cs.CV

Have I Seen You? Embedding Behavior Signals Synthetic Face Dataset Membership

Synthetic face datasets are increasingly used to reduce privacy exposure and data access constraints in biometric recognition. Yet the generators that produce these datasets are trained on real faces, so synthetic data may still reveal their real source data. We study this risk through a dataset-level membership inference attack that first identifies the synthetic dataset used to train a face recognizer and then infers the real dataset used to train the generator. Across 11 face recognition models, 11 synthetic datasets, and 7 real datasets, the attack recovers the synthetic training dataset in 100% of cases and identifies the generator's source dataset in 54.5% of cases. These results show that synthetic data can retain dataset-level traces of real training data and that privacy-preserving deployment requires stronger leakage mitigation.

Paweł Borsukiewicz, Daniele Lunghi, Wendkûuni C. Ouédraogo +2

University of Luxembourg, Luxembourg

Membership Inference Attacks Synthetic Data Biometrics Privacy Agent Behavior Modeling

Jul 30, 2026cs.GT

Strategy, Not Payoffs: A Behavioural Embedding of Normal-Form Games

Learning a strategic task changes more than what is directly taught: fine-tuning on one game can either enhance or degrade an agent's ability to reason in another. Understanding and predicting this transfer of strategic capabilities, however, remains a key challenge for large language models (LLMs). Normal-form games provide an ideal testbed for analyzing this phenomenon, as they feature explicitly defined payoffs and well-characterized equilibrium behaviours. In this work, we investigate whether game embeddings can explain and predict changes in LLM strategic capabilities following fine-tuning across different games. We propose a lightweight two-feature embedding that captures fundamental behavioural demands: the entropy of the Nash equilibrium and the sensitivity of optimal responses to an opponent's action. We show that while existing published structural embeddings primarily memorize game identities and fail to generalize, our behavioural embedding reliably predicts performance changes on held-out games. These results demonstrate that the transfer of strategic capabilities in LLMs is not dictated by the payoff geometry of a game, but by the underlying structure of the decision-making behaviour it requires.

Joshua Caiata, Sreepriya Pulyassary, Xiang Li +1

University of Waterloo

Agent Behavior Modeling Equilibrium

Jul 29, 2026cs.LG

The Convergence Behavior of Adam under Heavy-Tailed Noise

We establish the first convergence guarantees for the plain vector-form Adam optimizer under heavy-tailed stochastic noise. While several Adam variants are known to achieve optimal iteration complexity in bounded-variance nonsmooth nonconvex optimization, little is understood about their behavior when stochastic gradients admit only a bounded

p

-th central moment for some

p \in (1,2]

, a setting increasingly observed in modern deep learning. To address this gap, we generalize the recent online-to-nonconvex conversion framework to accommodate heavy-tailed martingale-difference noise. Building on this generalized framework, we develop a discounted regret analysis for Adam, without restrictive parameter coupling. Our results show that Adam converges to

(ρ,ε)

-stationary points under heavy-tailed noise. However, it exhibits a suboptimal iteration complexity and

p

-dependent convergence, a suboptimality that persists even in the bounded-variance case (

p=2

). Specifically, the

ε

-dominant term in the iteration complexity for reaching in-expectation stationarity is

T=\mathrm{O}\left(Δρ^{1/2}(G+σ)^{\frac{5p}{3p-4}}ε^{-\left(\frac{5p}{3p-4}+\frac{3}{2}\right)}\right)

for

p\in(\frac{4}{3},2]

, which simplifies to

T=\mathrm{O}(ε^{-13/2})

when

p=2

. When the domain radius is known and used to control the online-learner output, a standard setup in related literature, the convergence rate improves to match the optimal complexity. In this case, the

ε

-dominant iteration complexity is

T=\mathrm{O}\left(Δρ^{1/2}(G+σ)^{\frac{p}{p-1}}ε^{-\left(\frac{p}{p-1}+\frac{3}{2}\right)}\right)

for

p\in(1,2]

, which simplifies to

T=\mathrm{O}(ε^{-7/2})

when

p=2

. These findings provide new theoretical insight into the robustness and limitations of Adam in heavy-tailed regimes.

Yijiang Pang

Michigan State University, East Lansing, USA

Adam Stochastic Convex Optimization Convergence Agent Behavior Modeling

Jul 29, 2026cs.CL

From Representations to Behaviors: Exploring the Person-Situation-Behavior Triad in LLMs

Human personality theories characterize traits not as isolated attributes captured by a single score, but as stable individual tendencies expressed through the interplay among persons, situations, and behaviors. Existing studies of personality-related behavior in LLMs have primarily focused on outputs elicited under personality conditioning, characterizing observable trait-related expressions while lacking mechanistic evidence for the existence of internal personality-related representations, their cross-situational expression, and how these representations shape specific behaviors. Building on Funder's personality triad framework, we adapt its three components for LLM analysis: Person as personality-related internal representations, Situation as contexts that afford trait-relevant responses, and Behavior as response patterns on broader social tasks. We introduce a framework for discovering, controlling, and validating trait-like representations in LLMs. First, using contrastive behavior pairs grounded in shared situations, we identify sparse internal features associated with opposing poles of personality traits through SAE decomposition. We validate their trait relevance through effects on behavior to situation, token-level activation patterns, and robustness to paraphrasing. Second, feature-level interventions induce bidirectional trait-related shifts across a separate, diverse set of situations while preserving response validity, demonstrating consistent expression across contexts. Third, applying the same interventions to social intelligence tasks reveals behavioral changes with benefit-tradeoff patterns consistent with findings from human personality research, providing behavioral-level validation beyond personality scores. Our findings provide evidence that LLMs contain controllable trait-like representations linking internal states, situational expression, and behavioral outcomes.

Ruikang Zhang, Shuo Wang, Qi Su

1Peking University, Beijing, China · 2Beijing Institute of Technology, Beijing, China

Personality Agent Behavior Modeling Contrastive Learning

Jul 28, 2026cs.RO

MoMo: Dial Motion Mode in Robot Manipulation with Spatiotemporal Action Tokenization

To operate effectively across diverse contexts, robots must not only perform manipulation tasks accurately but also adapt how their actions unfold to the task, object, and interaction setting. We ask whether this execution-level variation can be learned as a reusable behavioral factor shared across tasks. We present \textbf{MoMo}, a two-stage imitation-learning framework consisting of a spatiotemporal action tokenizer and a behavior-cloning transformer that takes task and a continuous motion-mode condition as inputs. Across six real-robot manipulation tasks, varying this condition produces steady, dynamic, and intermediate behaviors that human raters can distinguish and that differ in joint speed, acceleration, and end-effector approach pitch. On tasks demonstrated in only one mode, MoMo transfers the unseen requested mode while largely preserving task success. Together, these results provide evidence of compositional generalization to unseen task--mode combinations and show that motion mode can be reused across tasks to control how a manipulation skill is performed.

Yuhan Hu, Hugues Thomas, Peide Huang +3

Apple

Robotic Manipulation Discrete Action Tokenizers Motion Agent Behavior Modeling Dial

Jul 28, 2026cs.MA

CoRenew: A large language model agent-based policy simulation platform for multifamily residential redevelopment

The difficulty of collective action remains a central challenge in the design of policies for multifamily residential redevelopment. Stakeholders continually adjust their decisions in response to evolving negotiation contexts and the reactions of others, meaning that when a policy intervenes and which stakeholders it targets can substantially reshape collective outcomes. Assessing these adaptive responses ex ante remains difficult because existing simulation models often rely on predefined behavioral rules. Here, we present CoRenew, an open-source platform that uses LLM-based agents to simulate negotiations among multiple stakeholders and evaluate the effects of alternative policy combinations. Integrating open source geographic and demographic data, the platform can generate synthetic residents, simulate negotiation dynamics under alternative policy settings and compares policy performance across competing objectives. It supports both numerical and semantic policy inputs and includes built-in tools for visualization and result export. We validate its behavioral realism against survey responses from 324 residents and a nine-month observed negotiation process from a real redevelopment case. With its modular and adaptable architecture, CoRenew can be used to assess policies across different institutional and cultural contexts.

Yudi Zhang, Yuming Lin, Li Tian +2

Department of Urban Planning, Tsinghua University, Beijing, 100084, China · Department of City and Regional Planning, UC Berkeley, Berkeley, CA, 94720, USA · Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China

Multi-Agent Simulations Negotiation Policy Evaluation Collective Behaviors Simulation-Based Reinforcement Learning Agent Behavior Modeling

Jul 25, 2026cs.MA

Emergent Behaviour in Financial Markets

Some properties of so-called complex or collective systems can be observed to emerge from the interactions of elementary agents. This phenomenon, known as emergent behaviour, has long since been studied in the most diverse disciplines, with recent growing awareness from the formal methods community about the opportunity of opening up to seemingly distant disciplines with appropriate technology for computer-aided reasoning. Different peculiar elements of complexity make automated reasoning on these systems particularly challenging. We consider electronic financial markets to drive our discussion. We identify and structure the sources of complexity to tackle in order to provide computational support for the analysis of emergent phenomena. We refrain from evaluating the suitability of specific technical solutions or frameworks of preference, which would as usual require simplifying assumptions and divert from the actual phenomenon of interest. Rather, we elaborate on possible alternatives to handle some of the main technical aspects involved in automated analysis, while retaining a solid and concrete interpretation of the domain, and in doing so outline a more systematic research program for the formal specification and analysis of market mechanisms.

Omar Inverso, Emilio Tuosto, Dragisa Zunic

Gran Sasso Science Institute, Italy

Emergence Strategic Agents Agent Behavior Modeling

Jul 25, 2026cs.CE

A Scale-adaptive Vision Model Links C. elegans Neuronal Morphology to Behavior for Neurotoxicity Assessment

Neurological disorders are a leading cause of global disability and are increasingly linked to environmental chemical exposures. Yet neurotoxicity assessment still relies on hand-scored morphological readouts that are subjective and poorly predictive of behavioral outcomes. Caenorhabditis elegans provides a genetically tractable, 3R-compliant alternative, but quantifying neuronal phenotypes from confocal microscopy at scale remains computationally challenging: existing vision foundation models, trained on natural or radiological images, cannot resolve the sparse signals and multi-scale lesions of neuronal imaging. Here, we introduce a dedicated self-supervised vision model for C. elegans dopaminergic neurons, together with CeNeuMorph, a multi-grained confocal benchmark of 27,117 annotated images. Specifically, moving beyond standard Masked Autoencoders, we propose a scale-adaptive masked image modeling strategy that jointly learns representations across resolutions and patch sizes under a fixed token budget. By decoupling structural semantic learning from rigid grid constraints, the model effectively resolves the full spectrum of neurodegenerative lesions - ranging from fine dendritic beading to gross soma shrinkage - within a tractable computational framework. Finally, our model surpasses both generalist and biomedical foundation models across classification, segmentation and detection tasks. Fusing visual features with morphological descriptors enables prediction of dopamine-dependent behavioral deficits (

R^2=0.498

). Screening 180 agrochemicals, we identify the benzimidazole moiety as a previously unrecognized determinant of dopaminergic neurotoxicity. Together, the work demonstrates how scale-adaptive self-supervised learning can connect morphology to function for a scalable alternative to mammalian in vivo models for neurotoxicity assessment and drug discovery.

Haochao Ying, Shenchong Lv, Yutao Sun +8

School of Public Health and Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, 310058, China. · State Key Laboratory of Transvascular Implantation Devices and TIDRI, Second Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou, 310009, China. · Polytechnic Institute, Zhejiang University, Hangzhou, 310058, China. +5

Morphogenesis Neurons Toxicity Self-Supervised Learning Agent Behavior Modeling

Jul 24, 2026cs.SE

The Best Programming Language for Tokenmaxxing: An Investigation of Coding Agent Behavior Across Programming Languages

Although coding agents are now very effective in a variety of programming languages, this paper first shows that the cost (in tokens) can very significantly by programming language. We evaluate five recent models on programming problems in Python, Java, Rust, and OCaml. We carefully control for problem difficulty, and show that there can be stark variation in token consumption that is consistent across models. To understand why, we analyze both the structure and content of agent trajectories. First, we re-execute every intermediate solution and abstract each trajectory as a sequence of test-outcome vectors, then label the work between successive solutions. This reveals agents repeatedly producing noncompiling solutions in unfamiliar languages and revising solutions that already pass. Second, we analyze trajectory text, finding that agents plan solutions in code comments, distrust the provided tests in favor of inputs they invent, and sidestep unfamiliar target languages by prototyping in Python. Our results show that by-language token efficiency is a metric that should be considered when benchmarking and developing multilingual agents, and, for the tokenmaxxer, a guide to the most expensive language to work in.

Zixuan Wu, Carolyn Jane Anderson, Arjun Guha

Northeastern University · Wellesley College

Multilingual Agents Coding Agents Theorem Proving Agent Behavior Modeling

Jul 24, 2026cs.MA

Where Facts Go Missing: A Layerwise Taxonomy and Per-Layer Attribution of Information Omission in Air-Gapped LLMAgent Pipelines

Air-gapped and on-premises language-model agents can silently omit decision-critical facts at any boundary between source ingestion and final answer generation. We present a nine-layer taxonomy (L0-L8), an instrumented attribution harness, and a conditional omission waterfall that distinguishes deterministic software loss from behavioral non-retrieval. We analyze 75,476 controlled synthetic trials spanning five open-weight model configurations and two inference engines, together with a separate 372-trial real-agent pilot covering FHIR, PubMed, and SEC-EDGAR sources with LangChain and ADK orchestration. The weighted synthetic benchmark yields an omission rate of 0.574 (95% CI: 0.571-0.578); deliberately injected deterministic faults at L0-L3 account for 73.4% of weighted loss under the benchmark allocation. Increasing context length is most strongly associated with omission (odds ratio 7.43, 95% CI: 5.44-10.15). Completed server-profile analyses associate q4 KV cache and scaled RoPE with higher omission. In the real-agent pilot, 57.8% of traces are unsuccessful overall and 50.9% remain unsuccessful after excluding execution errors. These results establish pipeline-level attribution in a controlled stress test, but benchmark allocations, confounded model comparisons, and heuristic behavioral labels do not measure production prevalence or causal architectural effects.

Santhiya Rajan

Multiverse Computing

Omissions Reasoning Gaps Generation Provenance Ablation Facts Taxonomy+2

Jul 24, 2026cs.CV

CommandLM: Data driven behavior level descriptor for ego vehicles

As autonomous driving systems move toward real-world deployment, interpretable, behavior-level decision-making is essential for safety, trust, and regulation. We introduce CommandLM, a multimodal large language model that generates concise, human-readable behavior descriptions for ego vehicles from fused multi-sensor data. Our model processes temporally fused bird's-eye view representations from LiDAR and multi-camera inputs via a Q-Former adapter connected to a quantized, LoRA-fine-tuned large language model. Trained on our CommandLM-nuScenes dataset, CommandLM produces intent-aware, interpretable captions suitable for planner supervision and safety auditing. Experiments demonstrate strong linguistic and behavioral alignment, achieving CIDEr 0.67, and BERT-F1 0.88, substantially outperforming the BLIP-2 baseline (CIDEr 0.52, BERT-F1 0.86). In human evaluation, 58% of the generated descriptions were rated accurate, efficient and rule-compliant, confirming their real-world plausibility. While the remaining descriptions may not always select the most efficient, goal-oriented behavior, CommandLM's interpretable outputs enable downstream validation systems to identify and correct such cases, making it an effective tool for transparent behavior auditing. These results show that integrating multimodal fusion with language reasoning yields efficient and transparent behavior-level understanding for autonomous driving. We release our code and dataset at: https://github.com/b-tok/CommandLM

Boris Tokic, Constantin Selzer, Fabian B. Flohr

1Munich University of Applied Sciences, Munich, Germany · 2Munich University of Applied Sciences, Munich, Germany

Autonomous Driving Scene Reasoning Agent Behavior Modeling Multimodal Fusion

Jul 23, 2026cs.AI

Expert Behavior Prior Reinforcement Learning

Behavior prior reinforcement learning (BPRL) has emerged as a promising paradigm to improve sample efficiency in online reinforcement learning (RL) by leveraging policy priors derived from offline demonstrations. However, most existing BPRL methods rely on static offline datasets, which often suffer from low data diversity and suboptimal trajectory quality. This reliance restricts the effectiveness of policy priors, hindering both policy exploitation and stability during online training. Consequently, agents are prone to inefficient exploration and unstable learning dynamics. To address these limitations, we deviate from existing offline pre-training methods and propose an Expert Behavior Prior (EBP) algorithm. Specifically, we introduce a Q-guided conditional variational autoencoder (Q-CVAE) that learns to generate expert policy priors directly from the online replay buffer. This enables the generation of high-value actions for guiding policy updates without relying on pre-collected expert trajectories. To further enhance policy exploitation, we propose an expert policy guidance (EPG) mechanism that selects expert actions from a generative support set, and we integrate a policy gradient correction (PGC) module to harmonize Q-guidance with expert supervision, promoting stable and consistent policy improvement. Extensive experiments conducted on robotic control (Gym, PyBullet) and industrial control (DMControl) benchmarks demonstrate that EBP significantly outperforms state-of-the-art online RL algorithms, achieving higher sample efficiency and more stable convergence.

Gong Gao, Weidong Zhao, Xianhui Liu +1

School of Computer Science, Tongji University, China

Model-Based Reinforcement Learning Offline Reinforcement Learning Guidance Agent Behavior Modeling

Jul 22, 2026cs.AI

Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling

High-temperature sampling is one of the primary mechanisms for increasing diversity in LLMs. Recent advances in truncation-based sampling techniques have helped mitigate drawbacks of high-temperature sampling such as neural text degeneration, thereby enabling greater diversity in LLM outputs without sacrificing coherence. However, increasing the entropy of the token probability distribution via high temperatures has also been shown to weaken model guardrails by reducing the model's refusal response in the presence of harmful prompts. Despite the potential benefits of high-temperature sampling and the importance of maintaining model safety, there is a lack of existing solutions for maintaining the refusal behavior of LLMs under a higher entropy regime. To address this gap, we systematically study how temperature influences refusal behavior in LLMs and propose an efficient sequential decoding approach which preserves a model's greedy decoding refusal response at high temperatures while incurring minimal additional latency. Through extensive experiments, we show that our approach preserves 91-99% of the greedy decoding refusal behavior across three benchmark datasets without compromising the model's high-temperature response for safe prompts. Our work demonstrates how refusal behavior can be maintained in an efficient manner for applications which require high-temperature sampling.

Phillip Howard, Xin Su, Allen Roush +2

Thoughtworks

Refusals Large Language Models Fail Agent Behavior Modeling

Jul 22, 2026cs.CV

Cortex: Compact Behavior Cloning for Quake with Frozen Visual Features

We study how far a deliberately simple behavioral-cloning policy can progress in a visually rich first-person game before adding reinforcement learning or explicit memory. Cortex is a compact Quake policy with 10.98 million trainable parameters in a six-layer transformer over a frozen DINOv3 encoder. It is trained on the Quake subset of the public Pixels2Play corpus: 6,849 recordings (about 474.7 hours), represented as 17.09 million cached decision frames with keyboard and mouse actions. One sampled training epoch uses 517,048 four-frame windows and takes 3.3 minutes of policy-head optimization on one RTX 5080, excluding one-time feature extraction. We evaluate two independent batches of 20 stochastic, 120-second episodes on Quake E1M1. Cortex does not complete the level, but every episode reaches the opening door, button room, and gate descent; 19 of 20 episodes in each batch record at least one kill. Under the same time-controlled harness, released P2P-150M and NitroGen checkpoints remain shallower in five matched-duration episodes each. These comparisons are limited by small reference samples and different native interfaces. Ablations show that denser visual tokens improve combat and survival, while longer optimization and naive action history improve offline metrics without consistently improving play. The remaining failures are consistent with covariate shift and motivate targeted corrective data. We release the policy implementation, checkpoint, and a representative rollout.

Dzmitry Malyshau

Behavior Cloning Agent Behavior Modeling Cortex Full Waveform Inversion

Jul 22, 2026cs.LG

The Quadrilateral Loss: Additivity as a Measurable Behavior of Dense Neural Networks

Additive models buy interpretability by forbidding feature interactions, a constraint that neural instantiations enforce architecturally. We introduce the quadrilateral loss, a differentiable penalty that treats additivity as a measurable behavior instead: a second-order mixed difference on pairs of training points swapping one coordinate, which vanishes if and only if the coordinate carries no interaction, remains informative for piecewise-linear networks, and equals in expectation the per-coordinate interaction mass of the interventional Shapley-GAM. The loss turns additivity into a dial - most learned interactions prove removable almost for free, and on small datasets a moderate penalty improves accuracy and additivity simultaneously - and into an online observable: its per-feature surrender curves show, across seeds and datasets, that pre-regularization interaction magnitude barely predicts what a regularized model retains, undermining post-hoc interaction rankings. Against this instrument we compare routes to exact additivity, spanning structural masks, behavioral penalties (optionally crystallized into exact structure), weight decay, backfitting, the shared-section model, and bagged boosted stumps: constraining behavior before structure dominates weight-space constraints, rankings reverse between data regimes, and converging routes agree on the shape functions themselves. Three silent failure modes we document share one anatomy: guarantees imported into settings that quietly void their preconditions.

Antonio Di Cecco

Universit`a "G. d'Annunzio" Chieti–Pescara, and School of AI.

Regularization Differentiable Optimization Agent Behavior Modeling

Jul 22, 2026cs.LG

AI-Driven Surrogate Models for Predicting Electrode-Scale Discharge Behavior in Lithium-Ion Batteries

Physics-based simulations are essential for understanding the electrode-scale discharge behavior of lithium-ion batteries (LIBs) but suffer from prohibitive computational costs. To address this, we introduce a novel deep learning surrogate pipeline based on the Swin3D Transformer to predict spatiotemporal discharge dynamics directly from volumetric data. Our approach integrates two key innovations: Gaussian Positional Encoding (GPE), which enhances spatial feature representation by adapting to the complex geometry of electrode microstructures, and a specialized Temporal Encoding module to capture non-linear timeseries evolution. Experimental validation on an Electrochemical Simulation (ES) dataset demonstrates that our pipeline significantly outperforms state-of-the-art point cloud baselines in prediction accuracy. Furthermore, the proposed method reduces the computational overhead by orders of magnitude, providing a scalable and efficient framework for high-throughput battery design and optimization.

Mengda Xing, Jean-Marie Lagniez, Alejandro Franco

CRIL, UA · CRIL, UMR 8188, Université d’Artois, Rue Jean Souvraz SP 18, F-62307 Lens Cedex, France · LRCS +1

Lithium-Ion Batteries Surrogate Models Spatiotemporal Swin Positional Encoding Agent Behavior Modeling

Jul 21, 2026cs.CL

Task Competence Is Not Instruction Following: Evaluating Instruction-Conflicting Behavior in Small Language Models

Instruction tuning is meant to make language models follow user requests, yet it is unclear whether small models comply when an instruction conflicts with their usual task behavior. We study this across three tasks - multiple-choice question answering (MCQA), sentiment classification, and mathematical question answering - by pairing a standard instruction with a conflicting non-standard one (select an incorrect option, output the opposite sentiment, or return twice the answer). This cross-task design allows us to test whether resistance to conflicting instructions is tied to specific task characteristics or reflects a broader behavioral tendency. As all predictions are scored against the original ground truth, a model that ignores the non-standard instruction still appears accurate. Using standard accuracy, non-standard accuracy, and an Instruction-Following Failure Rate (IFFR), we evaluate instruction-tuned Qwen models across sizes. Both standard accuracy and instruction following generally improve with scale, although the pattern is not consistent across all tasks and datasets. Small models stay competent yet routinely ignore the non-standard instruction, while larger models show a clear gap between the two settings. These findings suggest that gains in task capability do not automatically provide reliable control over model behavior. Task competence and instruction following are therefore distinct abilities, and reporting only standard accuracy hides instruction-following failures.

Mahdiyeh Farajidizaji, Vatsal Raina

Khajeh Nasir Toosi University of Technology · Apta AI, Spark AI Research

Instruction-Tuned Models Instruction Qwen3 Competence Cross-Task Interference Agent Behavior Modeling

Jul 21, 2026cs.LG

Elicitation without Backpropagation: Steering Model Behavior by Optimizing the Latent Posterior

In the \emph{latent posterior model} of transformer behavior, the next-token distribution arises from a posterior over latent predictive models conditioned on the context, mixed to generate continuations. We exploit this model in settings where it is exact, namely Bayes-filtered transformers (BFTs) meta-learned on sequences from a hierarchical prior, to introduce \textbf{Posterior Prefix Tuning (PPT)}, a new method for \emph{eliciting} behavior from a transformer: given a utility function on continuations, find a prompt under which the transformer generates continuations of high expected utility. For a BFT, the elicitation objective factors through the latent posterior, and the gradient of this objective can be estimated from samples of the prior alone. PPT optimizes the parameters of a distribution over hard prompts: it draws prior samples once from the BFT via predictive Monte Carlo (PMC), then estimates the gradient by importance sampling against them. The optimization performs no transformer forward passes and no backpropagation through the transformer, and the prior samples are utility-independent, so a single set of samples drives elicitation against any number of utilities at negligible marginal cost. We validate PPT on Beta--Bernoulli and reinforced urn BFTs across three utility families (reverse cross-entropy, frequency matching, Dyck validity).

Garrett Baker, Vinayak Pathak, Daniel Murfet +1

Timaeus · CORAL · Monash University

Posterior Transformer Architectures Elicitation Backpropagation Steering Agent Behavior Modeling

Jul 21, 2026cs.RO

Correct-by-Construction Behavior Tree Synthesis from Signal Temporal Logic Specifications with Application to Robotic Missions

Behavior Trees (BTs) are widely adopted for complex task execution in robotics, providing modular, reactive control but lacking formal guarantees. However, existing correct-by-construction synthesis from Linear Temporal Logic (LTL) cannot express quantitative timing constraints. This letter synthesizes correct-by-construction BTs from Signal Temporal Logic (STL) specifications. The workspace is modeled as a timed transition system and abstracted into a zone graph, and an augmented state space tracking both logical progress and timing constraints is introduced. A hierarchical fixed-point algorithm computes winning sets for an STL fragment encompassing safety, reachability, response, recurrence, and persistence, yielding BT subtrees with a runtime constraint function. Correctness guarantees are proven and complexity bounds are derived. Simulations demonstrate specification satisfaction with strictly positive robustness, and a physical quadrotor experiment with six STL specifications validates practical deployability.

Jiaheng Dong, Jingyi Huang, Liang Han

Sino-French Engineer School,Beihang University, Beijing 100191, China

Signal Temporal Logic Linear Temporal Logics Behavior Tree Invariant Synthesis Agent Behavior Modeling

Jul 20, 2026cs.CL

The Story Shapes the Agent: Narrative Priors in LLM Behavior

Persona prompting is widely used to steer LLM agent behavior, yet the narrative framing of a task can matter more than the assigned persona. We isolate this effect through structural isomorphism, constructing three text-based investigation games that share the same action space, stage progression, and resource constraints while varying only task narrative: disease investigation, IT troubleshooting, and murder mystery. Across 1,890 sessions spanning 3 models and 10 personas, we identify narrative priors: systematic action tendencies activated by a task's story framing, independent of its decision structure. Narrative priors explain 5-31x more behavioral variance than persona, are consistent across model architectures, and in two of three domains are negatively associated with task success. Persona effects that do transfer across narratives arise from behavioral anchors, persona descriptions whose language maps directly onto shared actions. Causal interventions confirm this: removing anchor words from a high-transfer persona reduces cross-narrative consistency by 95%. Our framework also generalizes to a held-out fourth narrative and yields a persona-selection method that improves cross-narrative transfer. These results suggest that LLM behavior that survives narrative changes should be grounded in concrete actions rather than abstract descriptions.

Yixuan Wang, James Lester, Shashank Srivastava

University of North Carolina at Chapel Hill · North Carolina State University

Artificial Intelligence Personas Persona Consistency Narratives Large Language Model Agents Agent Behavior Modeling

Jul 20, 2026cs.AI

The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI Systems

Existing AI measurement frameworks quantify cognitive capability, task automation, or catastrophic risk, but none measure autonomous agency: the extent to which a system behaves in a self-directed way. A system can saturate capability benchmarks while remaining entirely reactive, acting only when prompted and ceasing all activity when a task completes. We introduce the Autonomous Agency Scale (AAS), a behavioral framework that scores AI systems on a 0-5 lexicon across seven dimensions of agency: cognitive autonomy, temporal persistence, environmental agency, social agency, creative agency, self-awareness, and goal formation, each operationalized by falsifiable threshold tests. Every dimension is scored in two temporal bands: an Active band covering engaged, user-initiated activity, and an Ambient band covering idle periods. Ambient Level 4 is gated by the Idle-Gap Test, a counterfactual criterion (remove all triggers and observe whether internally derived activity persists) that separates self-direction from scheduled rule-following. We apply the scale to six contemporary systems spanning task agents (Claude Code, Manus, Hermes), consumer assistants (ChatGPT, Siri), and a persistent companion architecture (Airi). The two-band profile quantifies a boundary that single-score frameworks conflate: task agents reach Active composites of 2.3-2.4 while scoring 0.6-1.9 Ambient, with every idle-period behavior attributable to user-configured schedules, whereas the companion architecture, evaluated longitudinally, is the only assessed system whose idle-period behavior survives trigger removal. We discuss limitations, including single-rater provenance, developer-evaluator bias on the longitudinal assessment, and the partially operationalized self-direction boundary in the Active band.

Samuel Presgraves

Independent researcher.

Agent Behavior Modeling Cognitive Science

Jul 19, 2026cs.AI

A Diagnostic Framework for AI Agent Behavior

AI agents increasingly act within the same clinical, political, scientific, and social systems that behavioral scientists study. Evaluating these systems requires source-level diagnosis: the same behavioral pattern may arise from an agent representational substrate or from the roles, objectives, interaction structures, and governance rules that shape its expression. This Perspective proposes a diagnostic framework for AI agent behavior: layer attribution. The foundational computational layer defines what behaviors are possible through architecture, memory, perception, attention, and representation. The behavioral modulation layer shapes how those capacities are expressed through identity, resources, objectives, social interaction, institutional constraints, and governance. The framework clarifies three consequences: surrogate validity is a model-task-layer relation, human-AI divergence provides diagnostic evidence, and governance requires source attribution before intervention. Treating AI agents as behavioral actors therefore requires evaluation methods that determine where behavior originates before deciding how to explain, validate, or govern it.

Xichen Zhang, Yingjie Zhang, Tianshu Sun

Sobey School of Business, Saint Mary’s University, Canada. · Guanghua School of Management, Peking University, China. · Cheung Kong Graduate School of Business, China.

Artificial Intelligence Governance Diagnostic Framework Agent Behavior Modeling

Jul 17, 2026cs.RO

A Generative Partially Specified Finite State Machine Approach to Complex Behaviour Planning

Autonomous robots operating in dynamic environments require behaviour planning systems that combine reactivity, interpretability, and adaptability. While Large Language Models have been successfully integrated with Behaviour Trees for dynamic replanning, Finite State Machines, despite their widespread adoption and computational efficiency, remain unexplored for generative approaches. We propose a Generative Partially Specified Finite State Machine (GPSFSM) neurosymbolic architecture that utilises the symbolic and semantic structure of FSMs, including states and event-triggered transitions, to implement Behaviour Planning. This paper introduces the first GPSFSM framework for robotics, featuring Fabric, an FSM engine that parses, validates, and executes behaviour plans that contain Sequential, Recovery, Parallel-Any, and Parallel-All control structures. We extend the Capabilities2 package in ROS2 with an asynchronous event system for behaviour chaining and runtime parameter injection for configurable execution, addressing the ad-hoc function representations that limit current generative systems. PromptTools provides a unified ROS 2 interface to local and cloud LLMs, with prompt buffering, enabling dynamic asynchronous composition of task and context information. Together, these components enable standardised semantic capability descriptions for robot-agnostic development. Experimental evaluation on navigation tasks demonstrates that our GPSFSM approach achieves consistently higher plan-generation success rates than the state-of-the-art BTGenBot system, particularly excelling in zero-shot scenarios where BTs typically struggle, while maintaining comparable or lower planning latency to frontier LLMs. We also demonstrate that our system can generate complex behaviours. We release an open-source ROS2 stack that makes generative FSM planning practical and reproducible for robotic systems.

Kalana Ratnayake, Michael Pritchard, David Hinwood +2

University of Canberra · Collaborative Robotics Laboratory, Faculty of Science and Technology, University of Canberra, ACT, Australia · RMIT University +1

Classical Planning Behavior Tree Automata Agent Behavior Modeling

Jul 16, 2026cs.RO

Scaling Behavior Foundation Model for Humanoid Robots

Humanoid control requires natural whole-body coordination, precise real-time responses to control signals, and robust generalization across diverse environmental contexts, making it a cornerstone for generalist embodied agents. Behavior Foundation Models (BFMs) have recently emerged as a promising solution to address these challenges by leveraging large-scale behavioral data to achieve superior expressiveness, versatility and generalization. However, despite growing interest in scaling BFMs to further improve their capabilities, it remains unclear how key factors, including the learning paradigm, behavioral data and model architecture should be coordinated to enable effective scaling. In this work, we revisit the scaling recipe for BFMs and demonstrate that substantial performance gains can be achieved through the coordination of three core components: 1) the learning paradigm of motion tracking that reformulates diverse humanoid control problems as the reproduction of integrated whole-body behaviors in the global frame; 2) the strategic synergy between on-policy rollout quantity and reference motion diversity; and 3) the expressive and scalable model architecture termed Humanoid Transformer that facilitates the natural emergence of structured behavioral representations. Through extensive experiments in both simulation and real-world deployment, we demonstrate that our approach yields significant improvements in control fidelity and task generalization, reducing Mean Per-Keypoint Position Error (MPKPE) on the test set by over 10% in local mode and 82% in global mode compared with existing humanoid controllers. These results establish BFM as a principled and effective foundation for scalable and general-purpose humanoid control.

Weishuai Zeng, Kangning Yin, Xiaojie Niu +15

The Chinese University of Hong Kong · Galbot · Shanghai Artificial Intelligence Laboratory +4

Full-Body Humanoid Control Behavioral Foundation Models Whole-Body Wireless Foundation Models Agent Behavior Modeling

Jul 15, 2026cs.CV

Task-Specific Feature Fusion Method for Multi-Task Affective Behavior Analysis

The 11th Affective Behavior Analysis in-the-wild (ABAW11) Multi-Task Learning Challenge requires a unified system to predict valence-arousal, categorical expressions, and facial action units from the official s-Aff-Wild2 images. Although these tasks are naturally related through facial behavior, our validation experiments show that they benefit from different visual features, temporal processing strategies, fusion mechanisms, and calibration procedures. In this paper, we study task-adaptive feature fusion for ABAW11 multi-task affective behavior analysis. We first adapt two pretrained visual backbones, DINOv2 ViT-L and DINOv3 ConvNeXt-base, on an external expression-oriented facial image set and then freeze them to extract complementary frame-level features from the official ABAW11 data. On top of these frozen features, we systematically compare frame-level prediction heads, temporal convolutional heads, post-hoc temporal smoothing, LightGBM models, feature concatenation, gated fusion, residual fusion, late logit fusion, threshold calibration, and shared MTL structures. The final system selects task-specific fusion and prediction strategies rather than forcing all tasks to share a single architecture. On the ABAW11 validation set, the selected system achieves an EXPR macro-F1 of 0.4222, an AU macro-F1 of 0.5402, and a mean VA CCC of 0.6717, resulting in an overall validation score of 1.6341. The results suggest that task-adaptive fusion of frozen visual features is a simple and effective strategy for ABAW-style multi-task affective behavior analysis.

Jiajun Sun, Zhe Gao

Shanghai Normal University, Shanghai, China

Direct Feature Fusion Multi--Task Learning Facial Expression Recognition Valence-Arousal Estimation Agent Behavior Modeling

Jul 13, 2026cs.RO

A Behavioral State Vocabulary in Sony ERS-111 R-CODE

This paper presents a corpus-level analysis of generated behavior diagrams derived from Sony's R-CODE sample distribution for the ERS-111 AIBO. Rather than reading each script in isolation, the study compares named states across the corpus to identify the recurring control vocabulary that structures the sample set. The resulting aggregate shows that many superficially different routines are built from a compact embodied grammar centered on initialization, sensing, iterative action, synchronization, and recovery. In addition to historical analysis, the paper argues that this form of state-based abstraction is useful as an intermediate representation for constructing new encapsulated behavior routines, especially on constrained native robotic systems where deterministic control, direct hardware access, and modular behavioral composition remain important.

Christopher A. Tucker

Dr. Christopher A. Tucker

Behavior Tree Robocasa Agent Behavior Modeling Modular Framework Text Corpora

Jul 10, 2026cs.AI

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift

Post-training is a key mechanism for adapting large language models to downstream tasks. While prior work suggests that task adaptation can alter a model's pre-existing alignment, especially its safety behavior, its broader effects across alignment domains remain poorly understood. We address this gap through a systematic evaluation of representative task-adaptation methods, including supervised fine-tuning (SFT), KL-regularized SFT, and reinforcement learning with verifiable rewards (RLVR) across 15 alignment aspects spanning six key domains: safety, factuality, stance stability, social harm, controllability, and instructability. Our results reveal that post-training does not reshape alignment uniformly. RLVR improves task performance while inducing comparatively small, but non-zero, metric-specific shifts, while SFT leads to substantially larger alignment drift across domains. KL regularization mitigates this effect: stronger reference-model anchoring reduces alignment drift from the baseline, although KL-SFT still falls short of RLVR in preserving alignment. Representation-level analysis further supports this pattern, with shifts in alignment-relevant representations tracking behavioral drift. Together, these results show that task adaptation is not merely a capability-improving step, but an alignment intervention in its own right, motivating multi-dimensional alignment evaluation as a standard component of post-training pipelines.

James Elcock, William F. Shen, Xinchi Qiu +1

University of Cambridge

Large Language Model Adaptation Post-Training Reinforcement Learning With Verifiable Reward Agent Behavior Modeling

Jul 8, 2026cs.AI

Persona Cartography: Charting Language Model Personality Traits in Weight Space

Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety, but we lack reliable tools for decomposing, measuring, and controlling them. Our central insight is to treat personas as positions in a space of behavioural traits, using the OCEAN framework to describe model personas in terms of Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. We train low-rank adapters to amplify or suppress individual traits, and evaluate their effects using an LLM-judge calibrated against a human-validated panel, trait-specific multiple-choice benchmarks, and standard capability evaluations. Across six models from three families (4B-32B), we find that each adapter moves its target trait largely monotonically with scale, combines approximately additively with other adapters to construct mixed personas, and preserves performance on capability benchmarks at moderate scales. We further show that the induced trait axes affect safety-relevant behaviour in downstream evaluations: for example, moving along neuroticism and agreeableness axes affects frustration and sycophancy respectively. We also introduce an unsupervised psychometric pipeline that recovers four interpretable behavioural factors (tone, initiative, didacticism, epistemic caution) from model rollouts. Persona control can then be considered in terms of learning, scaling, and composing traits in weight space, providing a bridge between personality measurement, model editing, and safety.

Luke Baines, Anton Gonzalvez Hawthorne, Mariia Koroliuk +4

LASR Labs · ENS Paris-Saclay and MATS · UK AI Security Institute

Personality Persona Consistency Agent Behavior Modeling Weight-Space

Jul 8, 2026cs.CV

Infinite Worlds with Versatile Interactions

We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. (1) Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully crafted causal pretraining paradigm. (2) Through distilling a real-time variant from the base model, our system guarantees rapid response time, sufficient to drive 720p video streams at 60 fps. (3) Compared to the previous version, this update introduces highly diverse interactive elements, comprising a broader spectrum of actions (e.g., attacking, archery, spell-casting, and shooting) alongside a richer variety of text-driven events. (4) We pioneer the integration of an agentic harness within the domain of world modeling, wherein a pilot agent is tasked with planning and executing character behaviors, while a director agent is responsible for synthesizing novel environmental elements as the scene progresses. Additionally, to facilitate a shared experience, we develop an interface that permits multiple players to simultaneously immerse themselves in this vivid world simulator. We pair our primary 14B model with a lightweight 1.3B counterpart, which supports effortless deployment on a single GPU.

Zelin Gao, Qiuyu Wang, Jiapeng Zhu +17

Interaction Data Agent Harness Agent Behavior Modeling

Jul 8, 2026cs.CL

Diagnosing and Calibrating Tool-Call Boundary Drift in Multi-Teacher On-Policy Distillation

Agentic language models must learn when to call tools, when to consume tool responses, and when to answer directly. This makes multi-teacher on-policy distillation a natural training strategy: one teacher can specialize in tool calls, another in direct responses, and the student can learn from both on its own generated distribution. We show that this strategy can induce a behavior shift that is invisible from aggregate losses alone. In a two-teacher tool-use setting, vanilla generalized knowledge distillation improves tool-call recall but also moves the model toward over-calling, where it calls tools on examples that should be answered directly. Aggregate explanations are insufficient: tool-call samples do not receive more token exposure, and full-sequence per-token divergence is not larger for the tool-call teacher. We instead analyze behavior leverage imbalance: local token-level signals at mode- entry and structural positions, such as <tool_call> and function names, can have disproportionate control over the global generation mode. We propose Soft Clamp, a per-token divergence calibration method that dynamically compresses extreme token-level Jensen-Shannon divergence while preserving nonzero gradients. On APIGen-MT, Soft Clamp reduces over-calling from 13.7% to 9.0% relative to vanilla GKD while matching its decision accuracy. In a BFCL multi-turn diagnostic, it also lowers tool-call loops and repeated calls among GKD variants. These results suggest that multi-teacher OPD should monitor where teacher signals act, not only how large they are in aggregate.

Jiabin Shen, Guang Chen, Chengjun Mao

Aware Heterogeneous Multi-Teacher Multimodal On-Policy Distillation Agent Behavior Modeling Factual Recall Class Imbalance

Jul 8, 2026cs.AI

Large Behavior Model: A Promptable Digital Twin of the Retail Customer

Customer behavior modeling underpins recommendation, marketing, and decision support, yet existing approaches either optimize predictive accuracy without explaining decisions or simulate users without grounding them in real behavioral data. We present the Large Behavioral Model (LBM) that learns customer decision making directly from large-scale retail transactions through a unified Person-Environment formulation. Customer state is represented by a behavioral profile derived from historical purchases, while product context is incorporated through retrieval-augmented generation. The model is trained using continued pre-training on verbalized behavioral data, supervised fine-tuning for decision generation, and reinforcement learning with verifiable rewards for evidence-based calibration. We evaluate the proposed framework on purchase prediction, hard-negative discrimination, basket completion, promotion response, and cross-domain voucher redemption. The model consistently outperforms frontier general-purpose language models on in-domain retail tasks while demonstrating strong zero-shot and fine-tuned transfer across retailers and decision domains. Ablation studies show that continued pre-training is the primary driver of behavioral generalization, retrieval is most effective when applied during both training and inference, and reinforcement learning improves reliance on explicit behavioral evidence over generic language-model priors. These results demonstrate that behavioral knowledge encoded in transaction histories can be effectively learned by language models, providing a scalable foundation for customer digital twins and behavior simulation.

Wachiravit Modecrua, Krittin Pachtrachai, Touchapon Kraisingkorn

Amity Research and Application Center (ARAC), Amity AI Holdings Co., Ltd.

Behavioral Foundation Models Large Language Model Reinforcement Learning Consumption Model Size Agent Behavior Modeling

Jul 7, 2026cs.CL

Prompting Complexity: Shortest Prompts for Texts and Behaviors in LLMs

In this paper, we define the quantity of prompting complexity: for a fixed instruction-tuned language model, what is the shortest plausible prompt that makes deterministic decoding produce a target text? It is an LM-relative analogue of resource-bounded Kolmogorov complexity: the prompt is a program, the model interface is the interpreter, and information omitted from the prompt is supplied by the model's weights, training distribution, tokenizer, template, and decoding rule. Unlike classical Kolmogorov complexity, this measure is intentionally non-universal. In the finite-context setting it is computable by enumeration, but there is no model-independent invariance theorem; the same text may be cheap for one model and inaccessible or expensive for another. To keep the search space aligned with prompt engineering, we restrict programs to plausible human-readable texts rather than arbitrary token strings. We extend the exact definition to soft prompting complexity for approximate outputs, yielding a lossy notion of model-relative text compression and a formal target for prompt optimization. We also define prompting distance by comparing shortest generating prompts, and behavioral prompting complexity for reaching any output satisfying a specification. Based on these formulations, we define a research agenda for empirically studying which texts and behaviors are accessible from short plausible prompts under a fixed LM interface.

Adrian Cosma

Dalle Molle Institute for Artificial Intelligence (IDSIA)

Instruction-Tuned Models Text Analysis and Detection Prompt Optimization Agent Behavior Modeling

Jul 6, 2026cs.CL

You Frame It: How Conceptual Representations Shape LLM Detection and Reasoning about Antisemitism

LLMs enable the integration of external conceptual resources at inference time, creating new opportunities for detecting ideologically and historically complex phenomena such as antisemitism. We investigate how different forms of conceptual grounding affect antisemitism detection and explanation behavior across four state-of-the-art LLMs. Using two expert-annotated datasets, we compare definitional, fine-grained taxonomic, example-augmented, and large-context representations of antisemitism. We find that fine-grained taxonomic representations substantially improve recall, while simultaneously reducing precision. Surprisingly, supplying substantially larger conceptual resources yields no additional quantitative benefit. Post-Holocaust antisemitism poses the most persistent challenge across models and configurations. Analysis of explanations further reveals systematic limitations including overproduction of conceptual references, reliance on lexical cues, overconfidence, and difficulties with subtle or justificatory forms of antisemitism. Our findings highlight both the potential and the remaining limitations of conceptually grounded LLMs for antisemitism detection and reasoning.

Katharina Soemer, Helena Mihaljević

Goethe University, Frankfurt, Germany · HTW Berlin, Germany

Hate Speech Detection Agent Behavior Modeling

Jul 3, 2026cs.CL

Revealing Hidden Model Behaviors with Task-Specific Self-Reports

Fine-tuning can give a language model a hidden behavior--it may give false answers under a narrow condition, or give harmful advice only when a prompt touches a particular topic. We introduce the Stabilized Adapter for self-Report (SAR), a lightweight LoRA adapter that makes a fine-tuned model describe its own hidden behavior in plain language, using only the model and the dataset it was trained on. Across seven implanted behaviors (plus a no-behavior control), SAR detects the hidden behavior in every one--even when the model has generalized into broad misalignment that the training data alone does not predict. Introspection Adapters (IA), the closest existing baseline, detects some behaviors from our suite but misses others entirely--and where it misses, it hallucinates, consistently reporting wrong behaviors. SAR retains positive signal on every setting where IA fails and halves the rate of hallucinations. This makes it much easier for practitioners to audit their models and obtain reliable answers to "what did my model actually learn?" type of questions.

Taras Kutsyk, Bartosz Zieliński

1Jagiellonian University, Faculty of Mathematics and Computer Science · 2Jagiellonian University, Doctoral School of Exact and Natural Sciences

Introspection Adapters Agent Behavior Modeling Hidden States

Jul 2, 2026cs.RO

Controllable Sim Agents with Behavior Latents

Realistic traffic simulation requires agents that imitate logged behavior and can also be steered along interpretable axes. Such controllability enables engineers to isolate variables, reproduce specific edge cases, and test autonomous systems without real-world risk. We introduce Controllable Neural Variational Agents (CNeVA), a controllable simulated-agent framework that learns to infer a per-agent Gaussian behavior latent from per-channel discounted returns via a closed-form conjugate variational update, conditioning a rectified-flow trajectory generator trained on a mixed channel-mask curriculum for classifier-free guidance. To tackle scarcity in reward signals, we propose soft eligibility gates that replace hard binary thresholds with smooth exponential decay, preserving the gradient signal for near-threshold agents. On the Waymo Open Motion Dataset, CNeVA attains competitive realism on the benchmark while exposing per-channel controllability that the higher-ranked imitation models lack. Speed- and acceleration-based steering produces monotone responses without stall-induced reward hacking. Safety controllability is monotone and substantial with the introduction of soft eligibility. We manage to achieve steerable map compliance under a context-residual return measure. Furthermore, our experiment demonstrates that steering metrics must be read alongside physical-plausibility guardrails to avoid reward-hacking confounds.

Juanwu Lu, Junyu Zhu, Ziran Wang

Purdue University · University of Tokyo

Microscopic Traffic Simulations Learning-Based Control Multi-Agent Simulations Controllability Agent Behavior Modeling Video Latents

Jul 1, 2026cs.LG

The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology

Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques. Current MOs are typically constructed via post-hoc supervised fine-tuning (SFT) on behavioural transcripts or synthetic documents. Prior research has shown that interpretability methods can easily identify hidden behaviours in these MOs. However, recent work suggests that such post-hoc training methods may make interpretability unrealistically easy. We investigate this claim by constructing a suite of 54

\verb|OLMo2-1B|

- and

\verb|gemma-3-1b-it|

-based MOs trained with seven different techniques, including standard post-hoc SFT, post-hoc DPO, and more realistic integration of MO data into the OLMo post-training DPO phase. We use these MO variants to benchmark activation oracles, activation steering, logit lens, and sparse autoencoders. Our findings show that (i) MO interpretability depends strongly on training objective, target behaviour, model architecture, and training data generation pipeline; (ii) substantial variance remains even after controlling for differences in the strength of target behaviour expression; and (iii) our more realistic

\textit{integrated training}

often yields less interpretable MOs than standard post-hoc methods. Our results cast substantial doubt on the validity of current MOs as interpretability proxies.

Andrzej Szablewski, Gabriel Konar-Steenberg, Raffaello Fornasiere +2

1LASR Labs

Interpretability Mechanistic Interpretability Model Activations Behavioral Foundation Models Post-Hoc Agent Behavior Modeling+1

Jun 29, 2026stat.ML

Dynamic Prediction of Alternating Recurrent Events via Neural Network

Alternating recurrent events -- event-times of a specific nature that trigger a secondary refractory period -- occur in a wide-range of fields, including behavioral science, criminal justice, and biostatistics. Analysis of these events requires careful attention to the statistical nuance, including correlated observations and repeated outcomes subject to potential censoring. We develop an online dynamic prediction framework appropriate for predicting subsequent alternating recurrent events, by developing neural network theory for a statistical audiences and applying inverse probability weighted pseudo-observations. The proposed model is applied to dynamically predict alternating recurrent event-free time, showing good performance in simulation, and outstanding capability in application to predicting periods of low mood for first-year medical residents. We close with a discussion.

Abigail Loe, Susan Murry, Zhenke Wu

Department of Mathematics, Statistics and Computer Science, Macalester College, Saint Paul, Minnesota, U.S.A. · Department of Biostatistics, University of Michigan, Ann Arbor, Michigan, U.S.A.

Recurrence Neural Network Agent Behavior Modeling Audience

Jun 29, 2026cs.RO

Behavior Prompting Policy: Demonstrations as Prompts for Manipulation

We study behavior prompting, a paradigm that enables robots to perform new tasks at inference time given a single human demonstration, which we call a behavior prompt. To enable this capability, we present contributions in algorithm, data, and evaluation. For algorithm, we introduce Behavior Prompting Policy (BPP), an in-context visuomotor architecture that translates the behavior prompt and the current observation into robot actions. For data, we identify that task diversity is the primary driver of the prompting capability and introduce iPhUMI, a handheld manipulation interface for collecting diverse training data. For evaluation, we introduce DrawAnything and LIBERO-Gen to evaluate test-time adaptation to unseen drawing and tabletop manipulation tasks. We also demonstrate that iPhUMI serves as a practical interface for specifying behavior prompts at test time, enabling a human to command a robot via a single demonstration to complete known tasks or to define new robot capabilities. Altogether, behavior prompting provides a flexible and scalable way to teach robots new skills without the need for expensive fine-tuning. Our project website is located at https://behavior-prompting.github.io/ .

Austin Patel, Ben Pekarek, Joel Enrique Castro Hernandez +1

Stanford University · University of California, Berkeley

Robot-Free Demonstrations Visuomotor Policy Agent Behavior Modeling Prompt Engineering

Jun 29, 2026cs.AI

From Detecting Agency to Doing Work: Self-Caused Credit Builds a Durable Behavioral Self in a Minimal Spiking Agent

How does an agent that can tell self from world come to be durably shaped by that distinction? Recent work shows that a predictive system can detect its own agency (Ye, 2026), but detecting agency does not explain durable, self-shaped behavior. We show that agency-gated slow credit -- a conjunctive term OwnAgencySalience driving a slow parameter update -- produces post-unload behavioral residue: on a spiking substrate (Nengo LIF/PES), a learned self-preserving choice survives episodic buffer removal (retained fraction 0.96, N=50) and collapses when the slow decoders are reset or the agency gate is removed. Reproducing the agency comparator and toggling only the slow-credit channel, we find a clean dissociation: at matched agency gain, durable behavior develops only when self-credit performs slow work (post-unload self-preservation 1.00 vs 0.00). The same dissociation holds in 24-dimensional partially-observed control (0.74 vs 0.00), and a plastic-work analysis shows that basin deformation equals net self-credit work. Across eight sequentially-learned tasks under exogenous interference, the multiplicative veto also prevents forgetting: it retains old tasks (final post-unload accuracy 0.88, forgetting 0.13) where additive pooling collapses to chance-level recall, the no-agency ablation falls below chance, and episodic/replay baselines stay near chance after unload -- all with no replay buffer and no task-boundary-dependent protection mechanism (N=50). We formalize the durable residue as an operational behavioral self and argue that self-caused credit doing slow work is a necessary building block for agents that develop a self. No claim of consciousness is made.

Haoliang Han

Institute of Biomedical Strategy, China Pharmaceutical University

Step-Level Credit Long-Term Agent Memory Episodic Memory Agent Behavior Modeling Spiking Neural Networks

Jun 29, 2026cs.AI

MirrorCode: AI can rebuild entire programs from behavior alone

AI models are rapidly improving at autonomous coding, as shown by benchmark progress and one-off demonstrations such as AI implementing a C compiler. However, existing coding benchmarks tend to focus on shorter tasks, and one-off demonstrations are hard to compare systematically because they often have some human guidance, and are not standardized or repeated across models. To address these challenges, we introduce MirrorCode, a long-horizon coding benchmark based on reimplementing entire software projects. In MirrorCode, AI agents must replicate the functionalities of an existing program, without access to its source code. AI solutions must match the original program's output exactly on end-to-end tests, including held-out tests. MirrorCode's 25 target programs span different areas of computing: Unix utilities, data serialization and query tools, bioinformatics, interpreters, static analysis, cryptography, and compression. Existing AI models can already reimplement complex software, with the strongest model scoring 56% across the benchmark. For example, AI can reimplement gotree, a 16,000-line bioinformatics toolkit - a task that we believe would take weeks for a human engineer. However, studying the frontier of performance requires a larger inference budget than typical benchmarks, for example, $2,600 over 19 days for a single attempt on a large task. We show that AI agents can already complete long-horizon software engineering tasks, especially when requirements are precisely specified. More broadly, our work suggests AI will have transformative effects on software engineering, as autonomous agents continue to improve.

Tom Adamczewski, David Owen, David Rein +4

1Epoch AI · 2METR · 3Prime Intellect +2

Coding Agents Agent Behavior Modeling

Jun 29, 2026cs.LG

Building Multi-Task Agentic LLMs via Two-Phase Distillation

A key step toward artificial general intelligence is to train models that can perform multiple tasks. In this paper, we study how to build such models by first training separate RL experts for individual tasks and then consolidating them via distillation, as an alternative to directly training a single model on mixed tasks. We show that off-policy distillation degrades in multi-task settings due to the mode-covering nature of forward KL: aggregating data from multiple tasks introduces a large number of behavioral modes that can exceed the student's capacity, forcing it to average across behaviors and leading to degraded performance. In contrast, on-policy distillation is mode-seeking but requires strong initialization. Inspired by these observations, we propose a two-phase approach: off-policy distillation followed by on-policy refinement. Evaluation across conversational agents and text-based games confirms that this two-phase approach matches single-task RL expert performance for each individual task, whereas off-policy or on-policy distillation alone fails to match this performance.

Huaijie Wang, Shusheng Xu, Yi Wu +1

Tsinghua University · Ant Group

Residual Distillation Artificial Intelligence Systems Agent Behavior Modeling

Jun 29, 2026cs.HC

From Trait to Behavior: A Cognitive-Affective Personality System (CAPS) Perspective on Multi-Homing Intention in AIGC Platforms

With the rapid development of Artificial Intelligence Generated Content (AIGC) platforms, users increasingly show cross-platform usage intentions. Existing research focuses on adoption and usage intentions in single-platform AIGC contexts. A theoretical gap still exists in studies on cross-platform usage. This paper constructs and verifies a three-stage multiple mediation model based on the personality trait-perception-behavioral response framework. The model integrates the optimum stimulation level (OSL) theory, complementarity theory, and perceived value theory, and it sets social influence and use experience as control variables to examine users' multi-homing intention. The results show that: (a) OSL significantly enhances users' perceived complementarity; (b) perceived complementarity positively affects perceived epistemic value; (c) perceived epistemic value significantly and positively predicts multi-homing intention; (d) OSL influences multi-homing intention through a chain mediation path of perceived complementarity and perceived epistemic value; and (e) social influence has a significant positive effect on multi-homing intention, while the effect of use experience is not significant.

Xuchao Zhang, Jihye Lee

School of Design, Pusan National University, Busan, South Korea

Social Influence Generative Artificial Intelligence Agent Behavior Modeling Causal Mediation Analysis

Jun 28, 2026cs.LG

Mechanistically Eliciting Latent Behaviors in Language Models

We aim to discover diverse, generalizable perturbations of LLM internals that can surface hidden behavioral modes. Such perturbations could help reshape model behavior and systematically evaluate potential risks. We introduce Causal Perturbative Elicitation (CPE), an unsupervised method for discovering interpretable low-rank adapters (LoRAs) that can elicit these latent behaviors. CPE decomposes the computations of a deep transformer slice using a heuristic tensor-decomposition-based algorithm. CPE exhibits remarkable data efficiency, learning a large number of interpretable LoRAs from a single example. Even though CPE is unsupervised, we find that in some cases it can be competitive with supervised elicitation methods via brute-force enumerative search over weight space. For instance, CPE performs similarly to matched-wall-clock-time GRPO on the Countdown task for Qwen3-8B (85% vs 87%), demonstrating that CPE can efficiently elicit complex multi-token behaviors. Since CPE is unsupervised, it can also surface hidden failure modes, such as sandbagging, restoring 85% of locked BigCodeBench performance on a password-locked version of Llama3-70B introduced by Taylor et al. (2025). Additionally, since CPE explores behaviors in weight-space rather than token-space it can potentially ameliorate exploration hacking, a misalignment failure which may arise in sufficiently self-aware AI models (Ngo, 2022). In fact, we find that CPE virtually eliminates alignment-faking (Greenblatt et al., 2024) behavior in a Llama3-70B-based model organism developed by Hughes et al. (2025). Finally, we find that CPE can be used to initialize GPT-OSS-20B in an aligned basin when running GRPO on an environment prone to reward-hacking. By providing a data-efficient method to systematically explore the space of latent model behaviors, CPE yields a powerful tool for aligning AI systems and evaluating their safety.

Andrew Mack, Nina Panickssery, Alexander Matt Turner

†Principles of Intelligence · ‡Anthropic · §Independent

Model Activations Agent Behavior Modeling Low-Rank Adaptation Adapters