Sign in

Category: Other

  • Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models

    Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models

    Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models

    arXiv:2610.15218v1 Announce Type: new Abstract: A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the model runs, not when it is trained, and running fewer is cheaper and faster, so a deployment may choose to do it. Running fewer loops also makes these models less safe, and the loss of safety is larger than the loss of anything else we measured. We study four released Ouro checkpoints and Huginn-0125. At half of its trained depth, Ouro-1.4B-Thinking still solves 0.692 of the GSM8K maths problems, against 0.775 at full depth, keeping 89% of its accuracy. Over the same reduction, the rate at which it helps with harmful requests rises from 0.038 to 0.205, 5.3 times higher. The information is not lost: a linear classifier reads whether a request is harmful from the model's internal state after a single loop, with an ROC AUC of 0.967 against 0.986 at full depth. What the missing loops remove is the refusal that should follow. We measure the effect with four instruments, one generating no text at all, and reproduce it on a second model family. Removing a single direction from Ouro-1.4B's internal state at full depth drops its refusal rate on harmful prompts from 0.950 to 0.130, identifying what the shallow model is missing. Two run-time repairs do not help: the models' early-exit rules do not spend more loops on harmful requests, and choosing a depth per request does not recover the loss. Changing the training does. Standard safety training makes the shallow model safe only by refusing 0.865 of harmless requests, while training at randomly chosen depths reaches a separation of +0.399 between harmful and harmless refusal at one loop, against +0.118. On Huginn-0125 it keeps harmful help at or below 0.040 at every depth from 1 to 32 loops, where standard training reaches 0.194, and it costs no accuracy at full depth.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.15218

  • Trust Hinders Bidirectional Human-AI Alignment

    Trust Hinders Bidirectional Human-AI Alignment

    Trust Hinders Bidirectional Human-AI Alignment

    arXiv:2610.15136v1 Announce Type: new Abstract: Trust calibration remains the dominant framing of AI-assisted decision making: the goal is to close the gap between perceived and actual trustworthiness of AI systems so that users exhibit appropriate reliance on them. We argue that this approach, while useful for decision problems that are well-defined and clearly scoped, overly restricts what it means to make a decision with AI support. To overcome this limitation, we develop three dimensions of AI-assisted decision making. First, trusting AI is only one of several possible strategies for managing uncertainty. Second, trust calibration is often misapplied when AI models "large-world" decision problems, i.e., ill-defined situations where goals and states are only partially known or unknowable. Third, in such settings human-AI alignment requires addressing higher-order decision processes. We conclude by reflecting on the implications of our observations on the design of process-oriented human-AI coupled systems that jointly identify and negotiate uncertainty throughout the decision-making task.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.15136

  • Single-step Retrosynthesis via Reinforcement Learning from Forward Feedback

    Single-step Retrosynthesis via Reinforcement Learning from Forward Feedback

    Single-step Retrosynthesis via Reinforcement Learning from Forward Feedback

    arXiv:2610.15141v1 Announce Type: new Abstract: Single-step retrosynthesis is a one-to-many inverse problem, yet most models are trained and evaluated against a single recorded reactant set. Reference-based training gives no explicit positive signal for unrecorded alternatives, and exact-match evaluation rejects non-matching predictions regardless of chemical plausibility. We propose Retrosynthesis via Reinforcement Learning from Forward Feedback (RetroRLFF), which optimizes reactant generation using both reference agreement and forward consistency with the target product. Starting from a supervised decoder-only Transformer, RetroRLFF generates complete reactant candidates and uses a frozen forward reaction model to predict products. A sequence-level reward combines reference agreement and forward consistency while penalizing invalid outputs. Direct Advantage-Based Policy Optimization updates the policy without human preference annotations or a preference-trained reward model. On USPTO-50K, RetroRLFF outperforms all 14 baselines in candidate-level round-trip accuracy at k = 1, 3, 5, and 10. With approximately 50 million parameters, it achieves 90.1% top-1 round-trip accuracy, exceeding R-SMILES, the strongest competing baseline on this metric, by 8.5 percentage points. Compared with its supervised policy, round-trip accuracy increases from 83.1% to 90.1%, while exact-match accuracy is maintained at 57.9% versus 57.5%. In an anonymized expert assessment of 131 randomly selected test cases, organic synthesis experts prefer RetroRLFF over EditRetro in 67.9% of comparisons. These results support forward feedback as a training signal for improving forward consistency while retaining top-1 reference recovery. Expert assessment provides complementary evidence of synthetic feasibility on the selected cases, although neither forward consistency nor expert preference establishes experimental feasibility.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.15141

  • Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses

    Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses

    Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses

    arXiv:2610.15150v1 Announce Type: new Abstract: Recent work on self-evolving LLM agents treats the agent harness as an optimization target that can be iteratively improved through execution feedback. Existing approaches, however, largely optimize a single objective and evolve the harness as a monolithic artifact, limiting their ability to handle competing goals and to separate transferable design from environment-specific adaptation. We introduce Harmony Harness, a framework for multi-objective, compositional harness evolution. Harmony Harness formulates harness evolution as a multi-objective optimization problem and uses decomposition-based evolutionary search to maintain solutions across different regions of the Pareto frontier, avoiding reliance on a hand-designed structural diversity metric for repository-scale harnesses. In parallel, we introduce factorized evolution operators that separately refine general-purpose harness mechanisms and benchmark-specific adaptations, together with a dynamic composition workflow that integrates them at inference time. Across SecRepoBench and BaxBench, Harmony Harness consistently outperforms strong harness-evolution baselines, with gains exceeding 10% on both benchmarks. Our results show that explicitly modeling both objective trade-offs and harness structure yields substantially stronger and more transferable agent evolution than existing single-objective, monolithic approaches.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.15150

  • Self-Evolving Visual Agent via Margin Reward

    Self-Evolving Visual Agent via Margin Reward

    Self-Evolving Visual Agent via Margin Reward

    arXiv:2610.15084v1 Announce Type: new Abstract: Visual agents that interleave reasoning with tool invocation have posed a promising direction for multimodal tasks. However, learning effective tool invocation usually relies on curated question-answer pairs or expert demonstrations at scale, which are expensive to acquire. In this study, we propose Marvo, a simple-yet-effective self-evolution approach that enables learning tool invocation from unlabeled images. Marvo consists of two agents: (1) a challenger that generates question-answer pairs from unlabeled images, and (2) a solver that learns tool invocation by solving questions through reinforcement learning. To encourage effective tool invocation, a good training question should be difficult enough to warrant tool use, yet remain within the solver's capabilities. To this end, we introduce a margin reward to the challenger, defined as solver's performance difference with and without access to tools. With the margin reward, we create an adaptive curriculum that encourages the solver to learn effective tool invocation. Across benchmarks covering agentic reasoning, visual search, mathematical, and general real-world reasoning, Marvo improves average accuracy by up to 7.1\% — demonstrating margin reward as a preferred way to scale question complexity without human supervision.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.15084

  • Structural Chain-of-Thought: Reasoning with Executable Computational Graphs

    Structural Chain-of-Thought: Reasoning with Executable Computational Graphs

    Structural Chain-of-Thought: Reasoning with Executable Computational Graphs

    arXiv:2610.15107v1 Announce Type: new Abstract: Chain-of-thought prompting enables reasoning in large language models but produces explanations that are difficult to verify, expensive to generate, and not always faithful. We introduce a Structural Chain-of-Thought framework where models generate executable computational graphs instead of free-form reasoning. The final answer is obtained by deterministically executing the graph. The model is trained using graph-based reinforcement learning that rewards structural validity, answer correctness, and node overlap with reference graphs. Experiments across five benchmarks and four model families show that our method consistently improves accuracy over supervised graph training and can reduce generation length by up to 5-6x compared with standard GRPO and chain-of-thought supervised training. Our faithfulness experiments reveal that models trained with our approach tend to rely on deriving their answers from the generated graphs rather than producing post-hoc rationalizations as usually in chain-of-thought reasoning.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.15107

  • GesBench: When and Where Do Multimodal Language Models Perceive Social Meaning?

    GesBench: When and Where Do Multimodal Language Models Perceive Social Meaning?

    GesBench: When and Where Do Multimodal Language Models Perceive Social Meaning?

    arXiv:2610.15129v1 Announce Type: new Abstract: Human social perception is incremental: we infer intent before an utterance is complete, revise our interpretation as new cues arrive, and attend to specific facial, gestural, or prosodic signals that shape social meaning. Current multimodal LLM benchmarks largely evaluate final-answer understanding over complete episodes, rewarding post-hoc recognition of social meaning rather than the unfolding perception required for real-time interaction. Drawing on interactionally embedded Gestalt principles of multimodal human communication, we introduce GesBench: a human-grounded benchmark for cue-level social perception in multimodal LLMs. GesBench uses cumulative sub-utterance clips to measure when models form stable interpretations of speaker intention and social affordance, and human gaze-guided corruption to evaluate whether regions attended by humans are functionally important for model judgments. Built from more than 6000 utterance-level clips from scripted and unscripted conversational datasets, GesBench includes human annotations of unfolding judgments and gaze on a representative subset. Across open and closed multimodal models, we find a clear human-model gap: humans form predictive understandings early and revise more often, while models often hedge or repeat across different clips. GesBench shifts social evaluation from whether models eventually recognize meaning to when and where that meaning is formed. Our codes are publicly available at https://anonymous.4open.science/status/GesBench-share-212C.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.15129

  • Belief Embedding Tree Search

    Belief Embedding Tree Search

    Belief Embedding Tree Search

    arXiv:2610.15046v1 Announce Type: new Abstract: Beliefs in a Partially Observable Markov Decision Process (POMDP) are posterior distributions over the hidden state given the agent's history of actions and observations. They summarize everything the history says about the state, so planning in a POMDP is planning in a Markov decision process (MDP) over beliefs. Belief MDPs have continuous state spaces even for finite POMDPs, and exact planning in them is intractable in general. Planners must therefore approximate beliefs and estimate values. Monte Carlo planners do both inside a search tree, with an approximate belief at every node and a value estimate at every leaf. Approximations usually consist of sets of sampled states, with leaf values coming from rollouts, hand-designed bounds, or learned networks. Policies and values computed from these approximations are limited by their quality, and prior methods with learned networks rely on hand-chosen summaries of the sampled states. A belief representation should be computable from the parent node's representation through the POMDP's dynamics, let the search sample from it, and be learned so that it provides the information that policies and value functions need. We present Belief Embedding Tree Search (BETS), a Monte Carlo planner that meets these requirements by representing each node's belief with a generative distribution embedding (GDE) while updating it through the POMDP dynamics. BETS trains its belief model alongside its policy and value networks through experience, with the realized hidden state of the POMDP as the belief model's training target. We evaluate BETS on six configurations of RockSample, LightDark, and PocMan against BetaZero and three planners without learned components. BETS is competitive or leading on all six, while every baseline falls far behind on at least one. Where beliefs are highest-dimensional, it outperforms them by a large margin, even without search.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.15046

  • Trace Evolution Bench: Measuring Whether Agents Improve from Their Own Environment Traces

    Trace Evolution Bench: Measuring Whether Agents Improve from Their Own Environment Traces

    Trace Evolution Bench: Measuring Whether Agents Improve from Their Own Environment Traces

    arXiv:2610.15055v1 Announce Type: new Abstract: Self-evolving agents are usually scored by endpoint Gain: held-out success after an update minus success before. That difference can credit a frozen rescore as evolution. We introduce Trace Evolution Bench (TEB), a protocol that separates that rescore from a context or weight update, together with three frozen 80/20/40 packs. An update is accepted only when validation does not fall, held-out identifiers never enter the update, and a text update is not ranked with a weight update. The primary scoreboard is coding, graded by hidden unit tests in a closed workspace. On that pack (40 held-out tasks, one family), DeepSeek v4 Pro under no_evolve never changes its policy yet moves 7.5, 5.0, and 12.5 percentage points across three seeds. Of nine text-update cells inspired by GEPA, ACE, and ExpeL, seven have positive excess above that seed's own band, and one gepa_llm seed moves down by the width of its band (-12.5, regression 0.48). GLM and MiniMax do not reproduce that seven-of-nine pattern. No method stays above its own band on every seed of all three models: GLM has two paired cells above their own bands, and MiniMax expel_llm seed 44 is a third (regression 0.30). The methods were fixed on a validation screen before held-out was read. Office, graded by rule-bounded delivery, and manufacturing table QA are separate packs: office DeepSeek does not exceed its own bands (widest 17.5 points), and manufacturing has no paired positive excess beyond its seed band.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.15055

  • Exposing AI Inference as a Telco Network API over the 5G User Plane

    Exposing AI Inference as a Telco Network API over the 5G User Plane

    Exposing AI Inference as a Telco Network API over the 5G User Plane

    arXiv:2610.15062v1 Announce Type: new Abstract: Supporting edge Artificial Intelligence (AI) inference as a network service is challenging because current mobile systems can transport tensors but do not expose or understand the inference context that gives those tensors operational meaning. Prior studies have addressed this gap through dynamic partitioning, collaborative inference, and split pipelines; however, these solutions remain application-bound, network-blind, or context-free. This work proposes Inference on Demand (IoD), an inference-on-demand abstraction that exposes split inference through a CAMARA-like Application Program Interface (API) and carries a split-aware tensor context in-band across the 5G user plane path. We evaluate the IoD on a programmable user plane function (UPF)-based testbed using a partitionable visual AI workload, showing that adaptive split selection can operate as a network-facing service while avoiding the rigid cost profile of static configurations. Including our findings, split inference becomes more than offloading when the service intent, runtime partitioning, and tensor transport are made visible to the mobile data plane. This opens a path toward network-native AI services, in which programmable telco infrastructure coordinates computation, context, and connectivity for user-facing applications.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.15062