Searcharxiv⌕ Search

arXiv subjects

Natasha Jaques

Publications and source records attributed to Natasha Jaques.

At least 19 recordsLinked to original sources
arXiv2026

Tapes Together Strong: The Co-evolution of Computation and Cooperation

How does cooperation evolve in complex agentic systems? Prior work in evolutionary game theory studies why individuals are incentivized to cooperate by isolating social interactions from the physical costs of behavior, while artificial life models traditionally study emergent self-replication without formalizing the dilemma between acquiring resources and preserving the shared energy needed to reproduce. In contrast, we introduce Autopoietic Game Theory, a computational model where social interactions, replication mechanisms, and their associated computational costs are endogenous and simultaneously co-evolving. We study these dynamics using a computational substrate of randomly initialized programs in Z80 machine code, showing empirically, and motivating with a simplified theoretical model, that embedding a social dilemma directly into the physics of computation can favor the emergence of self-replicating, cooperative strategies. When resources are scarce, our analysis shows that defection can become self-limiting even in well-mixed populations: parasitic stealing destroys shared energy, slows execution, and can prevent reliable replication. Empirically, evolved programs suppress stealing across several Z80 environments, while spatial assortment further supports structural complexity and task performance. We further show that the framework can incorporate exogenous pressures, such as math tasks structured as sequential social dilemmas, when rewards are tied to computation budgets. These results suggest that coupling an agent's capacity for computation to its available energy transforms cooperation into a dominant scaffolding for building sustainable, self-organizing systems.

cs.MA↗
arXiv2026

Demystifying Reinforcement Learning Post-Training of Language Models

Reinforcement learning (RL) post-training has emerged as a powerful framework for enhancing the capabilities of large language models (LLMs), enabling impressive reasoning, math, and coding capabilities. Yet for many researchers and practitioners, the principles behind classical RL remain a "black box". In this work, we deconstruct the RL post-training algorithm, investigating each step to clarify what is actually happening beneath the surface. By isolating the mechanics of RL with Verifiable Rewards in a controlled and simplified environment, we examine how RL outcomes are shaped by the base model's prior distribution, the granularity of the reward signal, the diversity of the prompt distribution, and model scale. We use the entropy of the policy's output distribution as a lens to compare the distributions learned through pretraining, SFT, and RL post-training, revealing how each stage shapes model certainty. Our investigation sheds light on how these choices interact to affect post-training success. For example, we show that the effect of so-called 'spurious rewards' depends on the prompt distribution used for post-training. We also provide insight into why the success of RL post-training depends on whether the base model already places sufficient probability mass on the desired behavior, linking it to the classical concept of exploration in RL. Ultimately, we provide this primer as a resource to those in the NLP community wishing to incorporate RL as a tool in their toolbox.

cs.LG↗
arXiv2026

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Continuous self-improvement requires an ever-expanding pool of self-generated, diverse, adaptive goals. For language agents, existing training environment pools (hand-curated, statically synthesized, or frozen-verifier) keep the goal distribution fixed as the learner scales. We introduce SPADE (Self-Play in Adaptive Synthetic Executable Environments), a self-play RL framework in which a single LLM plays two roles: an Environment Designer that writes complete, long-horizon training environments as executable code with an OpenAI Gym-style reset()/step() interface, and a Reasoning Agent that learns to act in them. Each is a stateful, multi-turn environment (state transitions, reward functions, and verification code), so one interface spans reasoning problems and multi-step agentic tool use. The Reasoning Agent's regret is estimated using the gap between its reward with and without privileged hints; in optimizing this regret signal the Environment Designer learns to target environments at the edge of the agent's capabilities while keeping them feasible. Through extensive experimentation, we find several components critical to success: grounding the Environment Designer on documents sampled from a large pretraining corpus, and giving it an accumulated environment memory. Scaling to 30B-parameter models, SPADE improves over the strongest fixed-environment baseline by +5.3 on average across eight held-out math, science, code, and reasoning benchmarks, and lifts the tool-use setting by +5.7 on BFCL-v4 multi-turn and +13.9 on ACEBench-Agent; on the games setting, the margin over the strongest baseline grows with model scale. By making environment design itself a learnable component, SPADE takes a concrete step toward open-ended self-improvement.

cs.CL↗
arXiv2026

Debate Training Reduces Reward Hacking in RLAIF

We demonstrate that RL finetuning an LLM using debate, a two-player adversarial game between a generator and a critic adjudicated by a weaker LLM judge, reduces reward hacking compared to a reinforcement learning from AI feedback (RLAIF) baseline. Reward hacking is a central obstacle in RLAIF: as training progresses, the policy learns to exploit systematic errors in its AI judge, degrading task performance, a problem that worsens precisely when the judge is weaker than the policy, the setting most relevant to overseeing increasingly capable AI systems. We study mathematics tasks, where final-answer correctness is verifiable, allowing us to measure reward hacking dynamics. We train a Gemini~2.5 Flash-class policy with a frozen, weaker Gemini~2.5 Flash Lite judge, comparing a single-player RLAIF baseline against debate. While the baseline quickly hacks the judge, debate maintains judge performance throughout training, leading to a higher peak validation accuracy (45\% performance gap recovered) that persists through many RL steps. Additional experiments show that: 1) further weakening the judge leads to faster hacking, but this can be compensated by adding an additional debate round; 2) debate incentives override prompted misalignment; 3) RL using an LLM judge has a smaller train/validation reward gap than RL from verifiable rewards; 4) learning to critique to convince the judge using ground truth labels is possible but slow. Taken together, our results are a positive update on the feasibility of debate, while highlighting that balancing multi-agent training is critical: without player constraints, adversarial training risks defaulting to critic judge-hacking. We show that critique word limits (effective up to 150 words) successfully balance the game and avoid judge hacking, though this introduces a trade-off by restricting critic expressive clarity.

cs.LG↗
arXiv2026

Pigeonholing: how bad prompts hurt models, causing collapse and mistakes

While in-context learning is generally shown to be effective in Large Language Models (LLMs), bad contexts can cause performance degradation and mode collapse, a phenomenon we call "pigeonholing." **Unintentionally bad** contexts can happen without malicious jailbreaking intents: For example, a user asks the model to justify an incorrect math theorem or fails to correct the model's buggy code. Specifically, we investigate ``pigeonholing" in two scenarios: (1) when the user suggests a solution, and (2) when the conversation context includes the assistant's previous (incorrect) responses. Our experiments across 10 verifiable and open-ended tasks with 10 different models show that pigeonholing manifests in several ways: (1) repeating the incorrect answers from context (leading to 38-40% performance drop), (2) converging on a narrow set of answers in coding and text generation without exploring alternatives, and (3) flipping stance on controversial topics to align with the user or the assistant's previous claims. We find that pigeonholing worsens almost monotonically with the number of conversation turns (performance drops by additional 14+% as repeated mistakes increase from 1 to 5), and pigeonholing-induced mode collapse can happen even when the provided example is correct. As a step toward mitigation, we propose RLVR with synthetic errors which improves models by 43-60% under bad contexts compared to vanilla RLVR baselines.

cs.CL↗
arXiv2026

Do as the Romans Do: Learning Universal Behaviors from Heterogeneous Agents

Humans often acquire new skills by observing others, since observed behaviors implicitly reveal how to act in an environment. However, observations drawn from a heterogeneous population introduce conflicting behavioral signals, making it difficult to determine which behaviors are worth imitating. We address this challenge with General Reward Inference and Disentanglement (GRID), a social learning method that extracts universally useful behaviors from a heterogeneous population of demonstrators pursuing different goals. GRID decomposes per-agent reward functions into a general reward, capturing behaviors shared across all agents, and specific rewards, capturing individual preferences and objectives. Training exclusively on the general reward provides a new paradigm of generalist pretraining. It yields a generalist agent that internalizes universal environmental competencies, such as safety and basic task proficiency, without the mode-averaging bias that afflicts standard learning from demonstration techniques. This generalist serves as a superior prior for fine-tuning to downstream tasks, including preferences unseen during training. Experiments across a synthetic basis function decomposition, multi-agent Craftax, and a continuous autonomous driving simulator (Highway-Env) confirm that GRID successfully disentangles reward structure in a semantically meaningful way, outperforms standard learning from demonstration baselines, and enables more efficient and stable specialization.

cs.LG↗
arXiv2026

Embedded Arena: Iterative Optimization via Hardware Feedback

Embedded devices from wildlife monitoring stations to clinical wearables require local AI inference due to latency, communication, or privacy constraints. Optimizing models for heterogeneous microcontrollers (MCUs) requires simultaneously satisfying hard physical constraints on memory, power, and temperature while preserving accuracy, a multidimensional optimization that is today performed manually by experts. We ask whether an LLM agent can autonomously navigate this complex, multi-turn pipeline guided by real hardware feedback, and introduce a hardware-in-the-loop agent arena in which the agent iteratively refines both model and firmware -- compiling, flashing, and measuring on real hardware -- to enable closed-loop optimization. Frontier models, including Claude Opus 4.7 and Gemini 3.1 Pro, fail entirely without hardware feedback (0% deployment success), whereas our hardware-in-the-loop formulation achieves the first successful deployment within three iterations and can surpass human expert results within seven. This agentic co-optimization achieves 250x compression for vision models with <3.3% accuracy loss and 400x for audio with <6% Feature Error Rate loss, enabling battery-free operation on a commercial MCU via solar harvesting. We demonstrate practical impact in two real-world systems: an elk-detection camera trap (96.7% accuracy) and a phonetic-transcription wearable (8.44% FER) for child development research.

cs.AR↗
arXiv2026

Learn to Match: Two-Sided Matching with Temporally Extended Feedback

Two-sided matching markets often involve information that unfolds over time through interviews, repeated interaction, learning, and separation. Existing matching models typically reduce this process to immediate sub-Gaussian feedback about fixed preferences, missing settings where payoff-relevant information is revealed gradually and changes future matching decisions. We introduce a framework with temporally extended feedback, that formulates two-sided matching as a partially observable Markov game with costly pre-match screening, noisy post-match observations, evolving latent profiles, and endogenous continuation or dissolution. We instantiate this framework in Learn2Match, a multi-agent reinforcement-learning benchmark for dynamic matching markets. Learn2Match supports decentralized decision making over whom to interview, whom to match with, and when to dissolve a match, while evaluating policies using regret, social welfare, and an information-friction loss that measures the welfare gap caused by incomplete revelation of latent preferences. We find that independent PPO achieves higher cumulative social welfare and lower cumulative regret than the bandit-style CA-ETC baseline under temporally extended feedback, demonstrating the promise of MARL for dynamic matching markets. However, PPO still incurs higher information-friction loss, revealing that end-to-end MARL does not yet provide the coordinated exploration structure of matching-bandit methods. These results position Learn2Match as a benchmark for developing the next generation of matching-market algorithms: methods that are adaptive like RL agents, statistically disciplined like bandit algorithms, and structurally aware like stable-matching mechanisms. Please refer to https://sites.google.com/view/learn-to-match/home for the official website and the code link.

cs.LG↗
arXiv2026

Solipsistic Superintelligence is Unlikely to be Cooperative

AI's central challenge is shifting from capability to coexistence. The dominant paradigm in AI research focuses on developing powerful agents that treat the world as an exogenous and stationary source of feedback. We contend that superintelligence, an extremely capable task solver, born out of such a solipsistic approach to AI design, is unlikely to be cooperative. Deploying AI systems induces endogenous non-stationarity, resulting in a train-test-deploy gap where historical distributions diverge from the deployment context. We refer to this as the self-undermining property of unilateral optimization. Closing this gap requires AI that participates in cooperation: the equilibrium-selection process through which multiple actors navigate their interdependence. We call for a non-solipsistic research paradigm that treats this interdependence as a core design principle rather than approaching cooperation as a task to solve. This entails building dynamic evaluation testbeds involving adaptive counterparties, treating institutions as design primitives, and preserving human agency as a structural feature of the systems we build.

cs.AI↗
arXiv2026

Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents

Large Language Model (LLM) agents are increasingly deployed in settings where they interact with a wide variety of people, including users who are unclear, impatient, or reluctant to share information. However, collecting real interaction data at scale remains expensive. The field has turned to LLM-based user simulators as stand-ins, but these simulators inherit the behavior of their underlying models: cooperative and homogeneous. As a result, agents that appear strong in simulation often fail under the unseen, diverse communication patterns of real users. To narrow this gap, we introduce Persona Policies (PPol), a plug-and-play control layer that induces realistic behavioral variation in user simulators while preserving the original task goals. Rather than hand-crafting personas, we cast persona generation as an LLM-driven evolutionary program search that optimizes a Python generator to discover behaviors and translate them into task-preserving roleplay policies. Candidate generators are guided by a multi-objective fitness score combining human-likeness with broad coverage of human behavioral patterns. Once optimized, the generator produces a diverse population of human-like personas for any task in the domain. Across tau^2-bench retail and airline domains, evolved PPol programs yield 33-62% absolute gains in fitness score over the baseline simulator. In a blinded evaluation, annotators rated PPol-conditioned users as human 80.4% of the time, close to real human traces and nearly twice as frequently as baseline simulators. Agents trained with PPol are more robust to challenging, out-of-distribution behaviors, improving task success by +17% relative to training only on existing simulated interactions. This offers a novel approach to strengthen simulator-based evaluation and training without changing tasks or rewards.

cs.AI↗
arXiv2026

FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems

Multi-agent systems (MAS) powered by large language models (LLMs) increasingly adopt planner--executor architectures, where planners convert prompts into subtasks, roles, dependencies, and routing paths. This flexibility enables adaptive coordination, but exposes an attack surface in workflow formation: prompts can shape agent organization without modifying MAS infrastructure. We study this risk through social influence probing workflows to identify high-impact subtasks and malicious-signal propagation. The analysis reveals two vulnerabilities: workflow position can amplify or suppress a malicious signal, and sycophantic framing makes downstream agents more likely to relay it. We translate these findings into FlowSteer, a prompt-only workflow steering attack that converts vulnerability priors into one crafted prompt. FlowSteer aligns a malicious signal with influential task components and guides replanning toward dependencies that preserve propagation. Experiments show that FlowSteer increases malicious success by up to 55% over naive prompting, transfers across MAS setups, and remains effective with black-box topology inference. As FlowSteer biases the planning signals that generate the workflow, MAS defenses that inspect only the generated workflow provide limited protection. As such, we introduce FlowGuard, an input-side defense that reduces malicious success by up to 34% while preserving prompt utility. Our results position workflow formation as a new safety frontier for multi-agent LLM systems, opening a planning-time security perspective on how agent coordination itself can be attacked and defended.

cs.CR↗
arXiv2026

LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning

As language models are increasingly deployed for complex autonomous tasks, their ability to reason accurately over longer horizons becomes critical. An essential component of this ability is planning and managing a long, complex chain-of-thought (CoT). We introduce LongCoT, a scalable benchmark of 2,500 expert-designed problems spanning chemistry, mathematics, computer science, chess, and logic to isolate and directly measure the long-horizon CoT reasoning capabilities of frontier models. Problems consist of a short input with a verifiable answer; solving them requires navigating a graph of interdependent steps that span tens to hundreds of thousands of reasoning tokens. Each local step is individually tractable for frontier models, so failures reflect long-horizon reasoning limitations. At release, the best models achieve <10% accuracy (GPT 5.2: 9.8%; Gemini 3 Pro: 6.1%) on LongCoT, revealing a substantial gap in current capabilities. Overall, LongCoT provides a rigorous measure of long-horizon reasoning, tracking the ability of frontier models to reason reliably over extended periods.

cs.LG↗
arXiv2026

How LLMs Distort Our Written Language

Large language models (LLMs) are used by over a billion people globally, most often to assist with writing. In this work, we demonstrate that LLMs not only alter the voice and tone of human writing but also consistently alter the intended meaning. First, we conduct a human user study to understand how people actually interact with LLMs when using them for writing. Our findings reveal that extensive LLM use led to a nearly 70% increase in essays that remained neutral in answering the topic question. Significantly more heavy LLM users reported that the writing was less creative and not in their voice. Next, using a dataset of human-written essays that was collected in 2021 before the widespread release of LLMs, we study how asking an LLM to revise the essay based on the human-written feedback in the dataset induces large changes in the resulting content and meaning. We find that even when LLMs are prompted with expert feedback and asked to only make grammar edits, they still change the text in a way that significantly alters its semantic meaning. We then examine LLM-generated text in the wild, specifically focusing on the 21% of AI-generated scientific peer reviews at a recent top AI conference. We find that LLM-generated reviews place significantly less weight on clarity and significance of the research, and assign scores that, on average, are a full point higher. These findings highlight a misalignment between the perceived benefit of AI use and an implicit, consistent effect on the semantics of human writing, motivating future work on how widespread AI writing will affect our cultural and scientific institutions.

cs.CL↗
arXiv2026

Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data

While post-training has successfully improved large language models (LLMs) across a variety of domains, these gains heavily rely on human-labeled data or external verifiers. Existing data has already been exploited, and new data is expensive to collect. Moreover, true intelligence goes far beyond verifiable tasks. Therefore, we need self-improvement frameworks that are less dependent on external signals and more broadly applicable to both verifiable and non-verifiable domains. We propose **Mutual Information Preference Optimization (MIPO)**, a contrastive data augmentation method that constructs preference pairs by generating a positive response conditioning on the correct prompt, and a negative response by conditioning on a random, unrelated prompt. We show that using Direct Preference Optimization to learn from this paired data maximizes pointwise mutual information *under the base LLM* between prompts and model responses. Experiments with with 1-7B parameter Llama and Qwen instruct models show that MIPO achieves 3-16% gains (and 51% increase for Qwen2.5-1.5B-Instruct) on personalization compared to prompting baselines. Surprisingly, MIPO can also be useful in verifiable domains, such as math and multiple-choice question answering, yielding 1-20% gains *without any additional data or external supervision*. These results suggest a promising direction for self-improvement using intrinsic signals derived from contrastive data pairs.

cs.LG↗
arXiv2026

Improving Interactive In-Context Learning from Natural Language Feedback

Adapting one's thought process based on corrective feedback is an essential ability in human learning, particularly in collaborative settings. In contrast, the current large language model training paradigm relies heavily on modeling vast, static corpora. While effective for knowledge acquisition, it overlooks the interactive feedback loops essential for models to adapt dynamically to their context. In this work, we propose a framework that treats this interactive in-context learning ability not as an emergent property, but as a distinct, trainable skill. We introduce a scalable method that transforms single-turn verifiable tasks into multi-turn didactic interactions driven by information asymmetry. We first show that current flagship models struggle to integrate corrective feedback on hard reasoning tasks. We then demonstrate that models trained with our approach dramatically improve the ability to interactively learn from language feedback. More specifically, the multi-turn performance of a smaller model nearly reaches that of a model an order of magnitude larger. We also observe robust out-of-distribution generalization: interactive training on math problems transfers to diverse domains like coding, puzzles and maze navigation. Our qualitative analysis suggests that this improvement is due to an enhanced in-context plasticity. Finally, we show that this paradigm offers a unified path to self-improvement. By training the model to predict the teacher's critiques, effectively modeling the feedback environment, we convert this external signal into an internal capability, allowing the model to self-correct even without a teacher.

cs.AI↗
arXiv2026

Are Language Models Sensitive to Morally Irrelevant Distractors?

With the rapid uptake of large language models (LLMs) across high-stakes settings, it is becoming increasingly important to ensure that LLMs behave in ways that align with human values. Existing moral benchmarks for this purpose often prompt LLMs with value statements, moral scenarios, or psychological questionnaires, with the implicit underlying assumption that LLMs report somewhat stable moral preferences. However, moral psychology research has shown that even human moral judgements are sensitive to morally irrelevant situational factors such as the smell of cinnamon rolls or the level of ambient noise, thereby challenging moral theories which assume that human moral judgements are stable. Here we draw inspiration from this "situationist" view of moral psychology to evaluate whether LLMs exhibit similar cognitive moral biases. We curate a novel multimodal dataset of 60 "moral distractors" from existing psychological datasets of emotionally-valenced images and narratives, which have no moral relevance to the situation presented. After injecting these distractors into existing moral benchmarks, we find that moral distractors can shift the moral judgements of LLMs by over 30% even in unambiguous scenarios, highlighting the instability of LLMs' moral judgements and the need for more contextual approaches to AI alignment.

cs.CL↗
arXiv2026

AgenticRed: Evolving Agentic Systems for Red-Teaming

While recent automated red-teaming methods show promise for systematically exposing model vulnerabilities, most existing approaches rely on human-specified workflows. This dependence on manually designed workflows suffers from human biases and makes exploring the broader design space expensive. We introduce AgenticRed, an automated pipeline that leverages LLMs' in-context learning to iteratively design and refine red-teaming systems without human intervention. Rather than optimizing attacker policies within predefined structures, AgenticRed treats red-teaming as a system design problem, and it autonomously evolves automated red-teaming systems using evolutionary selection and generational knowledge. Red-teaming systems designed by AgenticRed consistently outperform state-of-the-art approaches, achieving 96% attack success rate (ASR) on Llama-2-7B, 98% on Llama-3-8B and 100% on Qwen3-8B on HarmBench. Our approach generates robust, query-agnostic red-teaming systems that transfer strongly to the latest proprietary models, achieving an impressive 100% ASR on GPT-5.1, DeepSeek-R1 and DeepSeek V3.2. This work highlights evolutionary algorithms as a powerful approach to AI safety that can keep pace with rapidly evolving models.

cs.AI↗
arXiv2025

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

Large Language Model (LLM) agents have demonstrated impressive capabilities for social interaction and are increasingly being deployed in situations where they might engage with both human and artificial agents. These interactions represent a critical frontier for LLM-based agents, yet existing evaluation methods fail to measure how well these capabilities generalize to novel social situations. In this paper, we introduce a method for evaluating the ability of LLM-based agents to cooperate in zero-shot, mixed-motive environments using Concordia, a natural language multi-agent simulation environment. Our method measures general cooperative intelligence by testing an agent's ability to identify and exploit opportunities for mutual gain across diverse partners and contexts. We present empirical results from the NeurIPS 2024 Concordia Contest, where agents were evaluated on their ability to achieve mutual gains across a suite of diverse scenarios ranging from negotiation to collective action problems. Our findings reveal significant gaps between current agent capabilities and the robust generalization required for reliable cooperation, particularly in scenarios demanding persuasion and norm enforcement.

cs.AI↗