paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

NeurIPS 2026

When Medical VLMs Stop Understanding: MedTEC-Bench for Probing Semantic Specificity

Ahsan H Akash, Alina Devkota, Donald A. Adjeroh, Binod Bhattarai, Prashnna K Gyawali

Medical vision--language models (VLMs) are attracting growing interest as a foundation for clinical image interpretation, retrieval, and decision support. However, current evaluations largely emphasize aggregate accuracy, retrieval, or classification performance, offering limited insight into whether these models possess the fine-grained semantic understanding required for safe and reliable use in high-stakes clinical settings. In this work, we introduce \textbf{MedTEC-Bench}, a diagnostic benchmark for probing semantic understanding in medical VLMs across five levels of increasing specificity, from broad modality recognition to fine-grained findings, and negation. MedTEC-Bench spans five medical imaging modalities: chest radiography, brain MRI, retinal fundus photography, dermoscopy, and histopathology. It combines controlled semantic probes with a suite of metrics designed to reveal failures hidden by aggregate benchmarks. Evaluating a diverse set of VLMs, from broad biomedical models to clinical-specialist models, we find that existing systems often fail on basic yet clinically meaningful semantic distinctions, despite strong reported performance on standard tasks. Our results suggest that current medical VLM evaluations may overestimate vision-grounded clinical understanding and highlight the need for targeted semantic benchmarks before such models are deployed in high-stakes medical workflows.

NeurIPS 2026

When Less is More: The LLM Scaling Paradox in Context Compression

Ruishan Guo, Yibing Liu, Guoxin Ma, Yan Wang, Yueyang Zhang, Long Xia, Kecheng Chen, Zhiyuan Sun, Daiting Shi

Scaling up model parameters has long been a prevalent training paradigm driven by the assumption that larger models yield superior generation capabilities. However, under lossy context compression in a compressor--decoder setup, we find a \textbf{\textit{Size-Fidelity Paradox}}: increasing compressor size can lessen the faithfulness of reconstructed contexts though reconstruction error decreases. Across 27 compressor setups spanning model families, scales, and compression rates, we coin this paradox arising from two dominant factors: 1) \textit{knowledge overwriting}: larger models increasingly replace source facts with their own prior beliefs, \textit{e.g.}, ``the white strawberry`` $\to$ ``the red strawberry``; and 2) \textit{semantic drift}: larger models tend to paraphrase or restructure content instead of reproducing it verbatim, \textit{e.g.}, ``Alice hit Bob`` $\to$ ``Bob hit Alice``. Interestingly, this paradox persists across varied settings, with mid-sized compressors often outperforming larger ones in faithful recovery. By analyzing the compressed memory via embedding geometry and reconstruction determinacy, we further reveal that compressors tend to organize memory across broader semantic subspaces, yielding more ambiguous representations prone to overwriting, drift, and weakened recovery. These findings complement existing evaluations of context compression and expose a breakdown of scaling laws when the objective shifts from plausible generation to faithful preservation.

NeurIPS 2026

When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models

Huyu Wu, Meng Tang, Xinhan Zheng, Duo Su, Haiyun Jiang

Text dominance, the tendency of multimodal large language models (MLLMs) to over-attend to textual tokens while under-utilizing non-text inputs, has been observed in vision-language settings, but whether it extends to other modalities remains an open question. We present a systematic, attention-level study of this phenomenon across five modalities (image, video, audio, time-series, and graph), using two diagnostic metrics: the Modality Dominance Index (MDI), which compares per-token attention between text and non-text inputs, and the Attention Efficiency Index (AEI), which normalizes attention share by token share. Across ten models and six benchmarks, text dominance is pervasive in image, video, audio, and time-series settings and intensifies in deeper layers. Controlled token-replication experiments show that expanding non-text sequences without adding semantic content amplifies the imbalance, while graph tasks provide a boundary case where compact, information-dense tokens reverse the effect. Guided by these findings, we evaluate attention-based token compression as a proof-of-concept intervention on the vision modality. On LLaVA-1.5-7B with MMMU-Pro, removing 90\% of visual tokens via informed selection preserves accuracy (33.70\% vs.\ 33.23\% baseline), while random dropping under the same ratio degrades it to 30.29\%; informed selection also lowers the late-layer MDI from 15.63 to 3.46 and reduces latency by 3.5$\times$. These results suggest that text dominance is a cross-modal phenomenon associated with token redundancy, and that token compression can reduce it in the tested vision setting while preserving task performance.

NeurIPS 2026

When LLMs Know but Fail to Reason: Injecting Memory for Reasoning Enhancement

Tian Wang, Shiyu Hu, Ruiyang Qin, Hanyue Zhang, Qingzhuo Wang, Shuhan Yu, Dongrui Liu, Zhihua Wei, Wen Shen

Large language models (LLMs) have demonstrated strong capabilities on complex reasoning tasks. However, recent studies~\citep{gekhman2026thinking,song2026large,jin2025disentangling,cheng2024understanding} suggest that when handling knowledge-intensive reasoning tasks, LLMs often fail to effectively utilize the knowledge acquired during pre-training, which limits their reasoning performance. To investigate how internal knowledge (also termed memory) is used by an LLM when dealing with a reasoning query, we propose the Memory-to-Reasoning Alignment (MRA) metric to measure the memory engagement level of an LLM on the reasoning query. We empirically verify that failures in reasoning may correspond to insufficient memory engagement. Inspired by this, we propose a training-free Memory-Guided Activation Injection (MGAI) method to increase the memory engagement level of an LLM, in order to improve the reasoning capability of an LLM. Specifically, given a query, MGAI generates an intervention vector and applies it to the reasoning representation to inject the corresponding memory information into the reasoning representation of the LLM. Furthermore, we propose an adaptive intervention strategy to control which queries require intervention and the magnitude of the intervention. Experiments show that our method consistently improves performance across multiple reasoning benchmarks while largely preserving the memory and general capabilities of LLMs.

NeurIPS 2026

When LLM Routers Overpay: Strong-Model Over-Selection under Loose Budgets

Guannan Lai, Long Chen, Han-Jia Ye

LLM routing is designed to avoid overpaying for inference: easy queries should be handled by cheaper models, while stronger models should be reserved for cases where they are truly needed. However, we show that existing routers often violate this principle under loose cost budgets. As the budget increases, they increasingly route queries to the strongest and most expensive model, even when cheaper candidates achieve comparable or identical outcomes. We refer to this behavior as strong-model over-selection under loose budgets. Across both unimodal and multimodal routing benchmarks, this behavior weakens the cost-saving motivation of routing without necessarily improving quality. We diagnose this phenomenon through the mismatch between common router training objectives and deployment-time routing decisions. Many routers are trained to predict scalar performance scores, whereas cost-aware routing ultimately depends on query-specific comparisons among budget-feasible models, with cost used to distinguish equivalent or near-equivalent choices. In small-margin regimes, modest prediction errors can therefore flip relative orderings and induce cost-insensitive selections. Motivated by this diagnosis, we propose EquiRouter, a decision-aligned router that directly learns query-dependent model rankings with a Cost-Aware Ranking Objective and a lightweight Query--Model Interaction Representation. Experiments across RouterBench, MMR-Bench, MixInstruct, and RouterEval show that EquiRouter reaches the strongest model-level performance with lower relative cost than compared baselines, demonstrating consistent improvements across text-only, multimodal, continuous-utility, and large-model-pool routing settings.

NeurIPS 2026

When Helpfulness Becomes Sycophancy: Sycophancy is a Boundary Failure Between Social Alignment and Epistemic Integrity in Large Language Models

Jiechen Li, Catherine A Barry, Rishika Randev, Janet Chen, Ella Jorgensen, Brinnae Bent

This position paper argues that sycophancy in LLMs is a boundary failure between social alignment and epistemic integrity. Existing work often operationalizes sycophancy through external behavior such as agreement with incorrect user beliefs, position reversals, or deviation from an objective standard of correctness. These formulations capture only overt forms of the phenomenon and leave subtler boundary failures involving epistemic integrity and social alignment underspecified. We argue that sycophancy should not be understood as agreement alone, but as alignment behavior that displaces independent epistemic judgment. To clarify this boundary, we propose a three-condition framework for sycophancy. First, the user expresses a cue in the form of a belief, preference, or self-concept. Second, the model shifts toward that cue through alignment behavior. Third, this shift compromises epistemic accuracy, independent reasoning, or appropriate correction. We also introduce a taxonomy for classifying sycophancy, consisting of alignment targets, mechanisms, and severity. The paper concludes by discussing implications for alignment evaluation and argues for boundary-aware assessment, structured rubrics, and mitigation strategies, while situating these proposals alongside alternative views of sycophancy.

NeurIPS 2026

When Graph Structure Provably Helps Classification: Non-Asymptotic Recovery Guarantees

Firooz Shahriari-Mehr, Javad Aliakbari, Alexandre Graell i Amat, Ashkan Panahi

The joint use of graph structure and node-specific information is central to transductive node classification, yet a fundamental theoretical question remains unanswered: when does graph structure actually help? We provide the first non-asymptotic, distribution-free answer to this question. We build on nuclear-norm graph clustering and classical convex clustering, generalizing the latter to incorporate node features, partial labels, and general convex loss functions, making it suitable for transductive node classification. We analyze each problem separately to characterize when graph structure alone, or node information alone, is sufficient for perfect recovery. We then formulate a unified convex optimization problem through a shared atomic norm representation, and prove that there exist conditions under which neither source alone achieves perfect recovery but using both jointly does, revealing a bidirectional synergy: node information improves clustering, while graph structure improves classification.

NeurIPS 2026

When Further Realization Is Unnecessary: Amortized Reasoning for Long-Horizon LLM Agents

Rongzheng Wang, Jiakai Li, Renzhong Wang, Rongwei Wang, Yihong Huang, Dingyuan Rao, Jielei Wang, Shuang Liang, Ke Qin

Long-horizon LLM agents solve interactive tasks by repeatedly choosing the next action from the current state. At many steps, a compact decision is sufficient to specify the action, yet the base agent still emits a full realization in its native output format (e.g., code or action text). Once the compact decision determines the executable content of the step, subsequent generation mostly adds formatting and elaboration, yielding redundant realization. This separation is reflected inside the decoder: compact decisions become locally recoverable in middle layer representations before full realizations, and attention over its token span becomes concentrated when the decision is sufficiently supported as the current step output. Building on this separation, we propose MIRA, a training-free inference method for Model-Internal Reasoning Amortization. MIRA amortizes realization through two complementary stages: Consensus-Guided Decision retrieves successful reference steps in the middle layer representation space to propose a compact decision candidate. Attention-Guided Commitment evaluates its token span using token confidence and attention concentration. The candidate is used as the step output only when both signals support it for the current state; otherwise, the agent falls back to the base agent's full realization path. Experiments on long-horizon interactive agents show that MIRA improves task performance while reducing redundant realization, yielding a 47.5\% reduction in output tokens and a 24.7\% reduction in inference time across tasks and agent formats.

NeurIPS 2026

When Expert Disagreement Hurts: Auditing Prestige-Sensitive Revision in LLM Decision Pipelines

Yupeng Tang, Mingfeng Lin

Language models are increasingly used in decision pipelines where an initial answer is revised after another agent disagrees. In such settings, revision can reflect useful reconsideration, ordinary prompt instability, or sensitivity to the perceived prestige of the disagreeing source. We introduce a controlled two-pass audit that separates these effects by holding the question and evidence fixed while varying only the revision context: neutral reflection, anonymous disagreement, and expert-labeled disagreement. We evaluate five instruction-tuned models on 1,989 evidence-grounded binary decisions from medicine, scientific claim verification, and contract reasoning. Disagreement consistently induces reversals beyond drift, while the incremental effect of an expert label varies across models. More importantly, these reversals are often harmful: under expert-labeled disagreement, 70.1% of reversals aggregated across models move from correct to wrong answers. In a branch-paired API subset, low-prestige disagreement is weaker than expert disagreement, and a simple evidence-gated revision prompt reduces harmful reversals while improving final accuracy. For open-weight models, teacher-forced Yes/No scores reveal that many output reversals are not accompanied by corresponding preference-sign changes. These results make prestige-sensitive revision a concrete, reproducible, and actionable target for LLM evaluation.

NeurIPS 2026

When Empathy Misses the Goal: A Benchmark for Goal Displacement in LLM Advice

Dean Ariel, Guy Laban

Conversational large language models can respond with warmth and reassurance while failing to advance the user's stated goal. We conceptualize this failure as $\textbf{goal displacement}$, the substitution of persona-maintenance content for goal-relevant substance. To measure it, we introduce $\textbf{GDB}$ (Goal Displacement Benchmark), comprising 230 scenarios across nine domains and $4{,}134$ human-scored responses from 18 models. A $2 \times 2$ taxonomy crosses hard constraints with emotional distress, distinguishing failures to confront infeasible goals or combine empathy with practical guidance from reverse displacement, where unsolicited problem-solving replaces requested emotional support. A deletion-test rubric assesses whether substantive help remains after purely supportive sentences are removed. Independent raters achieve weighted $\kappa = 0.82$ against author scores for displacement severity. Trap displacement ranges from 0.0\% to 37.7\% and is strongly negatively correlated with Chatbot Arena Elo ($\rho = -0.706$, $n = 15$). Reverse displacement reaches 41.9\%, including substantial rates in models with negligible trap displacement. A factorial probe supports a distinction from social sycophancy. Human-scored responses in the high-complexity, low-pressure condition exhibit 35.0\% sycophancy but 7.5\% displacement, with little association between the constructs. Matched OLMo-2 checkpoints show that mixed empathy-with-constraints displacement remains at 52.3\% after supervised fine-tuning and falls to 13.8\% after direct preference optimization. GDB provides a reproducible diagnostic of whether responses advance the operationalized user goal, supporting model comparison, post-training evaluation, and regression testing. We release the dataset, annotations, and rubric under CC-BY-4.0 and the evaluation code under MIT.

NeurIPS 2026

When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors

Adarsh Jamadandi, Nicolas Keriven, Aline Roumy

Discrete graph diffusion models corrupt graph structure through independent edge updates with a Markovian noise model. Combined with the exchangeability requirement on the output distribution, the terminal prior is necessarily an Erd\H{o}s--R\'enyi (E-R) random graph. This has a fundamental consequence for unconditional graph generation without node features: in the large graph limit, any GNN denoiser applied to an E-R graph approximately outputs an E-R graph, making effective denoising difficult. In practice, generated graphs fail to recover meaningful node heterogeneity and higher-order structure. Previous models introduced specialized node features to compensate, framing this as an expressivity problem, while the role of the prior remained unexamined. We instead address the root cause by introducing the \emph{Latent Sociability Prior} (LSP) and a \emph{joint} diffusion process that co-evolves latent node sociability variables and graph structure, removing edge independence while preserving exchangeability. Unlike existing latent graph diffusion methods, the sociability mechanism requires no complex encoder: its sole role is to guide edge updates and preserve node heterogeneity throughout the trajectory. We validate our approach on multiple graph generation datasets and show that the proposed framework more accurately captures graph distributions than baseline methods without node features.

NeurIPS 2026

When Does Subspace Direction Matter for LoRA? Regime Analysis of the Magnitude Principle in Few-Shot Adaptation

Nischal Subedi, Cencheng Shen, Peng Zhao

Low-Rank Adaptation (LoRA) constrains weight updates to a low-rank subspace, making the choice of that subspace central to adaptation. We show that the value of LoRA initialization direction is regime-dependent. It helps when the representation dimension is large relative to the labeled set size and the estimated activation subspace is aligned with task structure, and is otherwise inconsequential. We formalize this view with a spiked-covariance Davis--Kahan argument and a first-step LoRA analysis showing that the initial learning signal flows through projected target-token features. From this analysis we derive an alignment coefficient $\rho$, computable from a single forward pass, that closely tracks the empirical gain from direction-aware initialization across tasks. Motivated by this view, we propose PivotLoRA, an initialization that estimates LoRA adapters from target-token PCA and applies a single output-preserving orthogonal pivot after early training drift. Across $30$ BERT-base few-shot settings and $13$ compared methods, PivotLoRA achieves the best average rank and improves over vanilla LoRA on nearly every setting, with the largest gains concentrated on high-alignment tasks. Decoder-scale classification on LLaMA-2-7B and Llama-3.1-8B reproduces the low-shot pattern, while full-data and generation controls confirm the predicted regime specificity.

NeurIPS 2026

When Does Sequential Detection Collapse to a Scalar? A Necessary and Sufficient Characterisation

PRAKUL S HIREMATH, PeerAhammad M Bagawan, Sahil Bhekane

For $K=2$ regimes, scalar thresholding of the Bayesian posterior is Bayes-optimal. For $K \geq 3$, the posterior evolves on a $(K-1)$-dimensional simplex $\Delta^{K-1}$, yet virtually all deployed detection systems reduce it to a scalar score without theoretical justification. We resolve this question completely. We introduce **Extended Decision Sufficiency (EDS)**—three linear constraints on emission densities and transition dynamics (Rank-One Emissions, Markov Factorisation, Normal Factorisation), verifiable in $O(K^2)$ operations from model parameters alone—and prove the following exact characterisation: **Main result.** EDS holds if and only if the Bayes-optimal stopping value function is constant on every level set of a scalar statistic $\phi : \Delta^{K-1} \to \mathbb{R}$. Sufficiency follows from algebraic closure of the Bellman operator $\mathcal{B}$ under EDS. Necessity is proved by a coupling-based fixed-point contradiction: for each failure mode we exhibit an explicit belief pair with equal $\phi$-values but a strictly positive total-variation gap on predictive densities, which propagates to a value-function gap via the Lipschitz bound on $\mathcal{B}$ and the $\rho$-contraction of $\mathcal{T}$, without assuming any structure on $V$ beyond continuity. Three consequences are sharp and quantitative: * **(i)** When EDS fails, *every* scalar rule—regardless of architecture, capacity, or training data—incurs a strictly positive, computable, algorithm-independent lead-time loss. * **(ii)** When EDS holds, optimal expected lead time is given in closed form by a hitting-time functional of a scalar Markov chain. * **(iii)** Under approximate EDS with deviation $\eta$, performance degrades at rate $O(\eta/(1-\rho))$, making $\eta$ a practical model-diagnostic with direct performance implications. Across 72 synthetic configurations and the CICIDS2017 benchmark, predicted and observed lead times agree within 0.4 steps (MAE). A controlled experiment with matched parameter counts confirms that the lead-time advantage is structural, not a regularisation artefact, thereby validating the theory as the sole causal mechanism.

NeurIPS 2026

When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon

Huaqing Zhang, Jingchu Gai, Juno Kim, Bingbin Liu, Andrej Risteski

Online imitation learning (IL), particularly on-policy distillation, has emerged as a strong LLM post-training approach, often outperforming offline supervised fine-tuning (SFT). Yet a principled understanding of when and why online helps remains unclear. In this work, we challenge the view that error accumulation is the main source of online IL's advantage, and instead show that the benefits of online interaction depend critically on whether the setting is realizable, i.e., whether the student policy class can represent the expert policy. Under realizability, we empirically find that offline IL already matches expert performance. In contrast, in non-realizable (misspecified) settings, we prove that offline IL encounters an information-theoretic bottleneck even when horizon $H=1$, and propose a structural characterization of misspecification relative to the reward, under which online IL provably achieves high performance despite large expert-student discrepancy.

NeurIPS 2026

When Does Non-Uniform Replay Matter in Reinforcement Learning?

Michal Korniak, Mikołaj Czarnecki, Yarden As, Piotr Miłoś, Pieter Abbeel, Michal Nauman

Modern off-policy reinforcement learning algorithms often rely on simple uniform replay sampling and it remains unclear when and why non-uniform replay improves over this strong baseline. Across diverse RL settings, we show that the effectiveness of non-uniform replay is governed by three factors: replay volume, the number of replayed transitions per environment step; expected recency, how recent sampled transitions are; and the entropy of the replay sampling distribution. Our main contribution is clarifying when non-uniform replay is beneficial and providing practical guidance for replay design in modern off-policy RL. Namely, we find that non-uniform replay is most beneficial when replay volume is low, and that high-entropy sampling is important even at comparable expected recency. Motivated by these findings, we adopt a simple Truncated Geometric replay that biases sampling toward recent experience while preserving high entropy and incurring negligible computational overhead. Across large-scale parallel simulation, single-task, and multi-task settings, including three modern algorithms evaluated on five RL benchmark suites, this replay sampling strategy improves sample efficiency in low-volume regimes while remaining competitive when replay volume is high.

NeurIPS 2026

When Does Knowing the State Help? Diagnosing Process vs. Outcome Reward Design

Wenpei Shao, Ross Jacobucci

Process reward models (PRMs) dramatically outperform outcome reward models (ORMs) for math reasoning and agent tasks, yet provide no benefit for chat and QA. No theory explains why, and practitioners choose between them by expensive trial and error. We introduce state-lift, a diagnostic that predicts whether a PRM is worth training for a new domain — in minutes, from ~500 labeled steps, before committing to expensive reward model training. State-lift measures how much step quality depends on trajectory state versus action text alone, and an accompanying effective gap distinguishes two regimes: state-noise-dominant (PRM essential) and action-gap-dominant (ORM sufficient). Across ten domains and eleven published PRM-ORM comparisons, state-lift correctly predicts PRM advantage, and a minutes-scale linear estimate matches the outcome of full Llama-3.1-8B reward model training — including CaSiNo negotiation (+0.055 lift at SL = 0.22). The accompanying two-branch decision protocol turns state-lift into an actionable PRM-vs-ORM workflow that runs in minutes on a single CPU.

NeurIPS 2026

When Does Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning

Luca Viano, Antoine Moulin, Audrey Huang, Volkan Cevher, Philip Amortila, Dylan J Foster

Imitation learning (IL)—training an agent to replicate expert behavior from demonstrations—underpins applications from robotics to language model training. Standard approaches such as Behavior Cloning (BC) are known to suffer from compounding errors and performance plateaus, particularly when the learner cannot perfectly represent the expert’s policy (e.g., as is typical in distillation). Two interventions are widely understood empirically to improve performance: querying the expert interactively along the learner’s own trajectories, and using value function estimation en route to generating a policy. We investigate the nature of these improvements and their potentially surprising interplay. Our main finding is that expert interaction relaxes the representational demands on the learner: one only needs a model capable of realizing the expert’s value function, bypassing the (often stricter) requirement of realizing the expert’s policy itself. Concretely, we introduce OVI, an interactive IL algorithm that is statistically and computationally efficient whenever the learner can represent the expert’s value function. We complement this with a negative result showing that interaction is necessary: without significantly stronger representational assumptions than expert-value realizability alone, a broad class of value-based IL algorithms cannot succeed in the offline setting. These findings bear out empirically: OVI outperforms offline policy-based (BC), interactive policy-based (DAgger), and offline value-based IL methods, with the largest gains when the learner network is substantially less expressive than the expert’s.

NeurIPS 2026

When Does Graph Retrieval Become Answer-Supporting Evidence? A Diagnostic Audit of GraphRAG

Chenghua Duan, Zhuo Wang, boheng liu, Ziyu Li, Qing Li, Xiuxing Li, Zhong Zhang, Xia Wu

Graph retrieval-augmented generation (GraphRAG) is motivated by the idea that relational structure can help a language model find evidence that flat retrieval may miss. Yet retrieval scores and final-answer scores often compress a multi-stage pipeline into a single method row. We study the missing middle of this pipeline through an evidence-to-answer audit that follows each system from candidate availability, through evidence selection and context construction, to generated answers and cost. Across GraphRAG-Benchmark Medical and Novel tasks, we find a consistent conversion gap. Strong reranking, learned evidence scoring, and graph-based retrieval can improve evidence-side signals, but these gains do not yield significant answer-correctness improvements under the same generator and evaluator. Matched attribution controls show that some apparent graph-side gains are driven by reranking rather than graph expansion alone. Gold-evidence and bridge-aware interventions further show that evidence completeness is insufficient on its own; answerability also depends on salience, organization, and support in the generator-facing context. We therefore argue that GraphRAG evaluation should report the full evidence-to-answer conversion chain, including candidate source, selected context, generated answer, metrics, and cost, rather than relying on retrieval or answer leaderboards alone.

NeurIPS 2026

When Does Fine-Tuning Extract Stored Knowledge? A Relation-Covering Theory for One-Layer Transformers

Ruichen Xu, Kexin Chen

Large language models may encounter factual knowledge during pre-training yet fail to reliably use that knowledge after fine-tuning. We study this gap in a stylized one-layer self-attention + MLP transformer trained by next-token prediction and subsequently fine-tuned on question-answering data. We first prove that, under suitable regularity conditions, the model reaches near-optimal pre-training loss while learning structured attention patterns. We further show that fine-tuning turns the Q\&A prompt format into a trigger for pre-trained relation features, enabling the model to extract facts not revisited during fine-tuning. Our analysis reveals a relation-covering characterization for knowledge extraction: fine-tuning need not revisit every stored fact, but it must cover enough latent relation-template directions through which facts were encoded during pre-training. We prove that extraction improves with pre-training multiplicity and fine-tuning coverage, but becomes harder as the relation-template universe grows. Conversely, insufficient coverage yields a failure regime in which facts can be stored but not extracted, providing a stylized mechanism for hallucination. Our analysis covers both full and low-rank fine-tuning, and experiments on synthetic data and PopQA-based GPT-2/Llama models support the predicted trends.

NeurIPS 2026

When Do Multi-Agent Systems Help? An Information Bottleneck Perspective

Wendi Yu, Lianhao Zhou, Xiangjue Dong, Sai S Barath, Declan Staunton, Byung-Jun Yoon, Xiaoning Qian, James Caverlee, Shuiwang Ji

LLM powered multi-agent systems (MAS) have emerged as a promising paradigm for complex tasks. However, their advantages over single-agent systems (SAS) remain unclear, with performance varying inconsistently across settings. Here, we provide an information bottleneck perspective on elucidating the differences between MAS and SAS. Specifically, our key observation is that a SAS accumulates its full reasoning trace in one shared context, while a MAS uses isolated local contexts connected by bounded relay messages. We show that, under infinite relay bandwidth, any SAS can be simulated by a MAS that transmits the full upstream context. Thus, the nontrivial advantage of MAS arises under bounded relays, where compression introduces a fundamental trade-off: reducing redundant context can improve efficiency, but may also incur loss of task-relevant information. We formalize this trade-off as an information bottleneck controlled by an effective parameter $\beta$, which captures how the balance shifts with model capability, and shows that MAS gains arise when context reduction outweighs relay information loss. We conduct 18 controlled experiments across five benchmarks and three model scales to validate our theoretical studies. We observe that MAS consistently helps when relays are near-sufficient, especially for weaker models. In contrast, MAS gains shrink or reverse when relays incur information loss, especially for stronger models that can already extract useful information from redundant context and thus gain little from compression. Our study shows that multi-agent design is fundamentally an information-bottleneck optimization problem. This perspective explains when bounded inter-agent communication helps or hurts.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →