arXiv subjects

Chongming Gao

Publications and source records attributed to Chongming Gao.

At least 19 recordsLinked to original sources

arXiv2026

Learning Calibrated Confidence for Multi-Agent Collaboration

Complex information seeking on the Web often requires collecting evidence from multiple documents and reasoning across them, as in multi-hop question answering. Multi-agent systems address such tasks by dividing work among specialized agents, where upstream agents produce intermediate answers and supporting evidence that downstream agents build upon. However, upstream answers vary in correctness, and most systems provide no quantitative signal about it, leaving the downstream agent to judge whether to trust or verify what it receives based solely on the textual evidence. In this paper, we propose MASCAL. Each agent learns to produce a correctness probability for its answer by jointly optimizing task performance and confidence calibration in reinforcement learning; the upstream agent passes this probability at handoff, giving the downstream agent a quantitative basis for its decisions, and the final answer also carries a calibrated probability, quantifying the reliability of the system output. To guide the downstream agent in using this signal during training, we introduce confidence-aware weighting, which increases the learning weight at positions responsive to the upstream probability, so that the agent learns more from decisions where it actively uses the signal. Across three collaboration architectures spanning Web retrieval and reasoning tasks, MASCAL improves task accuracy and calibration quality for both agents, and generalizes to deeper collaboration chains and different model scales. Intervention analysis confirms that upstream confidence affects downstream decision behavior, and the learned final confidence supports selective answering and targeted rechecking.

cs.LG↗

arXiv2026

Locating and Closing Information Gaps in Multi-Agent Systems

Multi-step Web tasks often require several LLM agents to gather and combine evidence. The communication graph of a fixed workflow restricts which agents can read each other's outputs: evidence retrieved by one agent may never reach the agent that needs it, leaving an information gap and an incomplete or incorrect answer. Adding a connection can deliver the missing evidence, but can also lead the receiver to adopt an incorrect upstream conclusion that displaces a correct answer; the final output alone does not separate the two. We propose Selective Probing and Link Insertion for Closing information gaps in multi-agent Execution (SPLICE), which locates information gaps per query and decides what to adopt after adding an edge. After the original workflow runs, SPLICE uses the query and node outputs to locate a possible gap, adds one directed edge from a source to a receiver to deliver the relevant evidence, and re-executes the receiver and affected downstream nodes, producing a candidate answer. The adoption decision reads both the final answers of the two runs and the process changes the edit caused inside the workflow: how far the receiver moved, where its new content came from, and whether the change reached the final answer. A selector trained on these process features chooses between adopting the candidate answer and retaining the original. On five benchmarks, SPLICE raises the task score on Web tool use by 8.0% and the mean score on four reasoning and planning benchmarks by 5.7% relative to the static skeleton, at 1.25 to 1.44$\times$ the skeleton's cost, and transfers zero-shot to four unseen backbones.

cs.AI↗

arXiv2026

Select-TTT: Query-Conditioned Selective Fast Weight Updates for In-Place Test-Time Training

Test-time training (TTT) enables a deployed language model to internalize incoming context on-the-fly into a small set of fast-weight parameters, rather than merely treating it as transient context for attention. In-Place TTT recently made this idea practical for large language models by repurposing the down-projection of standard MLP blocks as fast weights. However, we find that its benefit largely disappears on realistic web long-context question answering. We attribute this to In-Place TTT's uniform write schedule: every chunk is written with equal strength, so irrelevant content dilutes query-relevant information in fast-weight memory. Building on this insight, we propose Select-TTT, a model-agnostic, query-conditioned rule for In-Place TTT that scales each chunk's write strength by its relevance to the user query. This relevance signal requires no supervision and no new parameters: it is read directly from the model's frozen output head, as the probability mass that a chunk's hidden states assign to the query tokens. A temperature-scaled softmax turns these scores into learning-rate multipliers, leaving the chunk-wise, context-parallel computation of In-Place TTT intact. Select-TTT consistently improves long-context question answering on two benchmarks and two backbones. These findings highlight the value of query-conditioned fast weight writes for practical test-time training on long-context question answering, which is also potentially promising for long-horizon agent tasks involving multiple user queries over evolving contexts.

cs.LG↗

arXiv2026

AutoRSE: Evaluating LLM Agents as Recommendation Engineers for Self-Evolving Recommender Systems

Recommender Systems Engineer Agents (RSE-Agents), which use LLM-based agents to autonomously improve recommendation algorithms, are emerging as a promising paradigm. However, their capabilities and limitations remain poorly understood due to the lack of a unified, standardized evaluation framework and systematic trajectory-level analysis. To address this gap, we introduce AutoRSE, an evaluation framework spanning six representative industrial-grade recommendation tasks, and conduct a large-scale empirical study of three frontier LLMs across three widely used agent harnesses. Our results show that RSE-Agents consistently enhance the performance of backbones on five of the six tasks, with an average relative improvement of 16.1%, indicating that they can already autonomously improve recommendation performance. However, trajectory-level analysis also reveals that current RSE-Agents function primarily as engineering optimizers rather than algorithmic improvers: their gains are largely driven by hyperparameter tuning, training strategies, and model ensembling, while genuine algorithmic innovations are rare. Since the largest gains in recommender systems often stem from algorithmic advances, this behavior underscores a fundamental limitation of current RSE-Agents. To probe this limitation, we perform idea-injection experiments and show that agents equipped with innovative ideas from frontier research or human experts achieve substantially larger improvements than those relying on self-generated ideas. These results suggest that idea generation is a central bottleneck of current RSE-Agents, highlights a key direction for the future recommendation system research. Our implementation is publicly available on GitHub: https://github.com/Ray-Tiann/AutoRSE.

cs.IR↗

arXiv2026

UserSWE: Evaluating Coding Agents in Multi-Turn Conversations with Dynamic Users

As coding agents become more capable, developers increasingly use them to fix bugs through multi-turn interactions. Existing benchmarks do not adequately cover this scenario. Most present a complete issue report in a single turn without interaction. Their evaluation can produce both false positives and false negatives, accepting incorrect patches or rejecting correct ones. We introduce UserSWE for evaluating coding agents' ability to fix repository-level bugs through multi-turn interactions with dynamic users and execution-grounded verdicts at every turn. Its construction pipeline turns repository history and existing single-turn benchmarks into multi-turn tasks. At each turn, information pools constrain what the simulated user can reveal, while a persona chain sampled from a transition model calibrated on 20,859 development sessions governs how it speaks. Tests run after every turn, and a pair of agents from different model families writes and gates each verdict, using test results as primary evidence and model judgment only for aspects the tests cannot resolve. We evaluate eleven agents on 72 tasks from 42 repositories and find that agent rankings change with the interaction budget. Claude Fable 5.1 resolves the most tasks in one turn, GPT-6-Astra resolves the most by the eighth turn, and Claude Opus 5 leads at most intermediate budgets. These results indicate that single-turn performance is insufficient to characterize interactive coding ability.

cs.AI↗

arXiv2026

When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration

Multi-agent LLM systems rely on message passing among specialized agents to accomplish complex tasks. However, an upstream agent may provide useful information or an incorrect answer that causes a downstream agent to override a correct answer supported by its own evidence. Prior work has not clearly separated the benefits of communication from the damage caused by incorrect messages. We study this problem with controlled experiments across five benchmarks and five receivers, keeping the downstream task and evidence fixed while comparing answers under three conditions: no message, the upstream agent's original message, or a message with the opposite conclusion. Our experiments reveal three key findings. First, messages often help when the downstream agent would otherwise answer incorrectly. Second, messages can also hurt: when the downstream agent would answer correctly without a message, an incorrect upstream message changes the answer in up to 32% of cases. Third, in 94% of audited harmful cases, the downstream agent copies the upstream's specific wrong answer--a pattern we term answer substitution. Removing unreliable messages recovers part of the lost accuracy, suggesting that communication should be selective based on upstream reliability and the evidence already available to the downstream agent.

cs.AI↗

arXiv2026

Beyond Verbalized Confidence: Calibrating Reasoners with Differentiable Readouts

Reinforcement learning with verifiable rewards (RLVR) trains reasoning models to produce correct answers, but does not ensure that their stated confidence is calibrated. The resulting models are systematically overconfident. Recent methods train calibration inside the RLVR loop by having the model state a numerical confidence alongside its answer, but they all obtain the confidence by sampling it as text. This choice imposes two costs: a sampled confidence introduces variance and in practice collapses to a handful of distinct values, and sampling makes the confidence non-differentiable, forcing the calibration loss through a scalar reward. We propose CREDO (Confidence REaDOut) to replace sampling with a deterministic readout. While RLVR optimizes correctness, CREDO reads the confidence from a dedicated token pair in the model's output distribution and trains it by differentiable regression. CREDO further turns the trained confidence into a signal for accuracy, weighting rollouts by how far confidence and outcome disagree, so that accuracy and calibration improve together. Across mathematical and code reasoning, CREDO attains the best accuracy and calibration, and the gains extend to abstention and selective prediction.

cs.LG↗

arXiv2026

Elastic Horizon: Discovering the Effective Interaction Frontier in Agentic Reinforcement Learning

Scaling the interaction horizon-the maximum number of environment interactions per episode-improves LLM agents on long-horizon tasks, and curriculum-based methods that progressively expand the horizon outperform fixed-horizon alternatives. However, existing schedules are open-loop: they monotonically increase the horizon until a manually specified maximum, with no mechanism to detect when further expansion stops helping. We propose the effective interaction frontier hypothesis: a dynamic boundary beyond which additional interactions yield diminishing returns while cost grows linearly. We then introduce Elastic Horizon, a closed-loop controller that tracks this boundary via the 90th percentile of successful trajectory lengths. On AppWorld and BFCL, fixed-horizon sweeps reveal clear saturation plateaus; Elastic Horizon stabilizes the horizon inside the saturation band from both under- and over-capacity initializations, attains the best success rates across 7B and 14B backbones, and saves up to 25% of per-step trajectory tokens. Our work shifts the paradigm from how to scale interaction horizons to when to stop scaling.

cs.AI↗

arXiv2026

Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation

Large language models (LLMs) have spurred interest in agent-based recommender systems, yet most agentic approaches remain user-centric: items stay passive entities whose exposure is a by-product of relevance ranking, which exacerbates exposure concentration and long-tail under-representation. We break this user-centric allocation of agency with a Tri-party LLM-agent Recommendation framework (TriRec). Responsibility is split deliberately: Stage 1 has each item generate self-promotion conditioned on the target user, which lowers cold-start barriers, while the exposure budget stays with the platform, whose Stage 2 sequential re-ranker balances relevance, item utility, and exposure fairness. On four public datasets TriRec improves accuracy, fairness, and item-level utility, with the accuracy gain significant on three of the four. A three-arm ablation at 50 candidates separates two levels of the mechanism on items that received no exposure during training: self-promotion drives the accuracy gain, and conditioning it on the target user adds further exposure, together raising these items' share of top-ranked exposure by 43.6% relative. Restricting promotions to catalogue-verifiable attributes cuts strong exaggeration to 0.5%/2.0% on two datasets while retaining 88.6%/92.0% of the accuracy gain. Our code is available at https://github.com/Marfekey/TriRec.

cs.IR↗

arXiv2026

RECAP: Feedback-Driven Streaming Semantic User Profiles for Short-Video Recommendation

Language-based user profiles convert long behavioral histories into explicit semantic representations for recommendation. However, most profile generators are optimized in an open loop: they may summarize past behavior fluently, but are not directly trained to improve future recommendation. We study this problem in real-world short-video recommendation, where user behaviors continuously arrive as streams and profiles must be incrementally updated under limited capacity. This requires maintaining a consistent bounded profile state and constructing profile-targeted semantic feedback from industrial implicit behavior logs. We propose RECAP, an offline closed-loop framework for optimizing streaming structured semantic profiles with historical recommendation feedback. RECAP maintains each profile as a bounded structured memory by combining LLM-based semantic updates with deterministic lifecycle and capacity control. RECAP constructs profile-targeted semantic feedback by filtering label-consistent behavior pairs with an LLM judge and training a dual-tower evaluator whose matching score serves as a GRPO reward. Experiments on Kuaishou short-video data show that RECAP improves uAUC by 0.0084 and Recall@2000 by about 4.9% over the base generator. Further analyses confirm the benefits of feedback construction and policy optimization, and show more grounded refinement and user-level abstraction in profile updates. A seven-day online A/B test further shows a statistically significant 0.139% improvement in average application usage time per user.

cs.IR↗

arXiv2026

The Pitfall of Scaling Up: Uncovering and Mitigating Popularity Bias Amplification in Scaling Transformer-based Recommenders

We identify a critical pitfall in scaling transformer-based sequential recommenders: while increasing model size improves recommendation accuracy, it simultaneously amplifies popularity bias. This bias drives systems to over-recommend popular items at the expense of niche ones, which not only undermines fairness but also degrades the broader ecosystem by reinforcing the Matthew effect and filter bubbles. Consequently, this bias amplification emerges as a fundamental obstacle to sustainable model scaling. Through comprehensive theoretical and empirical analyses, we uncover the root cause of this amplification. Our findings reveal that as model depth increases, the two core components of the transformer architecture, i.e., attention aggregation and feed-forward projections, synergistically induce severe spectral collapse in model predictions, which directly translates to the amplification of popularity bias. To address this challenge, we propose SPRINT (Scalable Popularity Regularization IN Transformers), which mitigates spectral collapse during scaling by constraining (i) the maximum column-sums of the attention score matrices and (ii) the spectral norms of the feed-forward parameters. Extensive experiments demonstrate that SPRINT significantly improves both accuracy and long-tail fairness. Crucially, it yields more favorable scaling behaviors when expanding model sizes from 0.05M to 0.34B parameters. The code is available at https://github.com/Tiny-Snow/GenRec.

cs.IR↗

arXiv2026

Uncertainty-aware Generative Recommendation

Generative Recommendation has emerged as a transformative paradigm, reformulating recommendation as an end-to-end autoregressive sequence generation task. Despite its promise, existing preference optimization methods typically rely on binary outcome correctness, suffering from a systemic limitation we term uncertainty blindness. This issue manifests in the neglect of the model's intrinsic generation confidence, the variation in sample learning difficulty, and the lack of explicit confidence expression, directly leading to unstable training dynamics and unquantifiable decision risks. In this paper, we propose Uncertainty-aware Generative Recommendation (UGR), a unified framework that leverages uncertainty as a critical signal for adaptive optimization. UGR synergizes three mechanisms: (1) an uncertainty-weighted reward to penalize confident errors; (2) difficulty-aware optimization dynamics to prevent premature convergence; and (3) explicit confidence alignment to empower the model with confidence expression capabilities. Extensive experiments demonstrate that UGR not only yields superior recommendation performance but also fundamentally stabilizes training, preventing the performance degradation often observed in standard methods. Furthermore, the learned confidence enables reliable downstream risk-aware applications. Our project repository is available at: https://github.com/cxfann/UGR.

cs.IR↗

arXiv2026

Trustworthy Recommendation in the Era of Large Language Models: Opportunities and Challenges

The field of recommender systems (RS) is currently undergoing two profound paradigm shifts. From the perspective of objectives, the goal has shifted beyond mere recommendation accuracy to comprehensive trustworthiness, encompassing multiple dimensions such as robustness, fairness, and privacy preservation. From a technical perspective, Large Language Models (LLMs) have been extensively integrated into RS, reshaping the foundations of recommendation through richer semantic understanding, stronger intent reasoning, and more flexible user interactions. The convergence of these two shifts prompts a timely and pivotal question: how does the integration of LLMs reshape the landscape of trustworthy recommendation? In this work, we present a systematic review of trustworthy LLM-empowered recommendation. By comprehensively analyzing over 200 recent studies, we reveal that the introduction of LLMs acts as a double-edged sword. While their advanced mechanisms and user-friendly interfaces offer unprecedented opportunities to enhance trustworthiness, they simultaneously introduce new risks, such as novel forms of bias and hallucination-induced issues. To characterize this dual impact, we systematically identify 13 opportunities and 18 challenges across six fundamental dimensions of trustworthiness, and accordingly organize the existing literature into a novel taxonomy. We also provide a comprehensive review of commonly used datasets and evaluation metrics to facilitate empirical validation. Finally, we identify critical open challenges and outline future directions, hoping to inspire future research on this emerging topic.

cs.IR↗

arXiv2026

Fine-grained List-wise Alignment for Generative Medication Recommendation

Accurate and safe medication recommendations are critical for effective clinical decision-making, especially in multimorbidity cases. However, existing systems rely on point-wise prediction paradigms that overlook synergistic drug effects and potential adverse drug-drug interactions (DDIs). We propose FLAME, a fine-grained list-wise alignment framework for large language models (LLMs), enabling drug-by-drug generation of drug lists. FLAME formulates recommendation as a sequential decision process, where each step adds or removes a single drug. To provide fine-grained learning signals, we devise step-wise Group Relative Policy Optimization (GRPO) with potential-based reward shaping, which explicitly models DDIs and optimizes the contribution of each drug to the overall prescription. Furthermore, FLAME enhances patient modeling by integrating structured clinical knowledge and collaborative information into the representation space of LLMs. Experiments on benchmark datasets demonstrate that FLAME achieves state-of-the-art performance, delivering superior accuracy, controllable safety-accuracy trade-offs, and strong generalization across diverse clinical scenarios. Our code is available at https://github.com/cxfann/Flame.

cs.LG↗

arXiv2026

Beyond Static Best-of-N: Bayesian List-wise Alignment for LLM-based Recommendation

Large Language Models have revolutionized recommender systems (LLM4Rec) by leveraging their generative capabilities to model complex user preferences. However, existing LLM4Rec methods primarily rely on token-level objectives, making it difficult to optimize list-level and non-differentiable metrics (e.g., NDCG, fairness) that define actual recommendation quality. While Best-of-N (BoN) directly optimizes these metrics during inference, its high computational cost hinders real-world deployment. To address this, BoN Alignment aims to distill the search capability into the model itself, yet current approaches suffer from two critical limitations: (1) Indiscriminate Supervision, where the static reference fails to distinguish the relative quality of candidates exceeding its empirical range, leading to a loss of ranking guidance; and (2) Gradient Decay, where the effective supervision signal rapidly diminishes as the evolving policy improves, resulting in inefficient optimization. To overcome these challenges, we propose BLADE (Bayesian List-wise Alignment via Dynamic Estimation). Unlike static approaches, BLADE introduces a Bayesian framework that continuously updates the target distribution by fusing historical priors with dynamic evidence from the model's current rollouts. This mechanism constructs a self-evolving target that adapts to the model's growing capabilities, ensuring the training signal remains informative throughout the learning process. Extensive experiments on three real-world datasets demonstrate that BLADE significantly outperforms state-of-the-art baselines. Crucially, it breaks the static performance upper bound, achieving sustained gains in both ranking accuracy (Recall, NDCG) and complex list-wise metrics (Fairness, Diversity). The code is available via https://github.com/RegionCh/BLADE.

cs.IR↗

arXiv2026

Position-Aware Drafting for Inference Acceleration in LLM-Based Generative List-Wise Recommendation

Large language model (LLM)-based generative list-wise recommendation has advanced rapidly, but decoding remains sequential and thus latency-prone. To accelerate inference without changing the target distribution, speculative decoding (SD) uses a small draft model to propose several next tokens at once and a target LLM to verify and accept the longest prefix, skipping multiple steps per round. In generative recommendation, however, each item is represented by multiple semantic-ID tokens, often with separators, and current drafts typically treat these tokens uniformly. This overlooks two practical facts: (i) a token's semantics depend on its within-item slot, and (ii) uncertainty tends to increase with speculation depth. Without modeling these effects, SD's speedups can be limited. We introduce PAD-Rec, Position-Aware Drafting for generative Recommendation, a lightweight module that augments the draft model with two complementary signals. Item position embeddings explicitly encode the within-item slot of each token, strengthening structural awareness. Step position embeddings encode the draft step, allowing the model to adapt to depth-dependent uncertainty and improve proposal quality. To harmonize these signals with base features, we add simple gates: a learnable coefficient for item slots and a context-driven gate for draft steps. The module is trainable, easy to integrate with standard draft models, and adds negligible inference overhead. Extensive experiments on four real-world datasets show up to 3.1x wall-clock speedup and about 5% average wall-clock speedup gain over strong SD baselines, while largely preserving recommendation quality.

cs.IR↗

arXiv2026

Sequence-aware Large Language Models for Explainable Recommendation

Large Language Models (LLMs) have shown strong potential in generating natural language explanations for recommender systems. However, existing methods often overlook the sequential dynamics of user behavior and rely on evaluation metrics misaligned with practical utility. We propose SELLER (SEquence-aware LLM-based framework for Explainable Recommendation), which integrates explanation generation with utility-aware evaluation. SELLER combines a dual-path encoder-capturing both user behavior and item semantics with a Mixture-of-Experts adapter to align these signals with LLMs. A unified evaluation framework assesses explanations via both textual quality and their effect on recommendation outcomes. Experiments on public benchmarks show that SELLER consistently outperforms prior methods in explanation quality and real-world utility.

cs.IR↗

arXiv2026

Medical Reasoning with Large Language Models: A Survey and MR-Bench

Large language models (LLMs) have achieved strong performance on medical exam-style tasks, motivating growing interest in their deployment in real-world clinical settings. However, clinical decision-making is inherently safety-critical, context-dependent, and conducted under evolving evidence. In such situations, reliable LLM performance depends not on factual recall alone, but on robust medical reasoning. In this work, we present a comprehensive review of medical reasoning with LLMs. Grounded in cognitive theories of clinical reasoning, we conceptualize medical reasoning as an iterative process of abduction, deduction, and induction, and organize existing methods into seven major technical routes spanning training-based and training-free approaches. We further conduct a unified cross-benchmark evaluation of representative medical reasoning models under a consistent experimental setting, enabling a more systematic and comparable assessment of the empirical impact of existing methods. To better assess clinically grounded reasoning, we introduce MR-Bench, a benchmark derived from real-world hospital data. Evaluations on MR-Bench expose a pronounced gap between exam-level performance and accuracy on authentic clinical decision tasks. Overall, this survey provides a unified view of existing medical reasoning methods, benchmarks, and evaluation practices, and highlights key gaps between current model performance and the requirements of real-world clinical reasoning.

cs.CL↗