LACUNA is a new testbed that injects PII into predefined model parameters to benchmark the localization precision of LLM unlearning methods, revealing that SOTA approaches are imprecise despite strong output performance.
super hub Mixed citations
Kimi K2.5: Visual Agentic Intelligence
Mixed citation behavior. Most common role is background (69%).
234
Pith papers citing it
Background
69% of classified citations
abstract
We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that two modalities enhance each other. This includes a series of techniques such as joint text-vision pre-training, zero-vision SFT, and joint text-vision reinforcement learning. Building on this multimodal foundation, K2.5 introduces Agent Swarm, a self-directed parallel agent orchestration framework that dynamically decomposes complex tasks into heterogeneous sub-problems and executes them concurrently. Extensive evaluations show that Kimi K2.5 achieves state-of-the-art results across various domains including coding, vision, reasoning, and agentic tasks. Agent Swarm also reduces latency by up to $4.5\times$ over single-agent baselines. We release the post-trained Kimi K2.5 model checkpoint to facilitate future research and real-world applications of agentic intelligence.
hub tools
citation-role summary
background 43
baseline 13
method 3
other 2
dataset 1
citation-polarity summary
claims ledger
- abstract We introduce Kimi K2.5, an open-source multimodal agentic model designed to advance general agentic intelligence. K2.5 emphasizes the joint optimization of text and vision so that two modalities enhance each other. This includes a series of techniques such as joint text-vision pre-training, zero-vision SFT, and joint text-vision reinforcement learning. Building on this multimodal foundation, K2.5 introduces Agent Swarm, a self-directed parallel agent orchestration framework that dynamically decomposes complex tasks into heterogeneous sub-problems and executes them concurrently. Extensive evalu
authors
co-cited works
years
2026 234representative citing papers
The Meta-Agent Challenge shows frontier AI models rarely match human-engineered agent baselines when tasked with autonomous development, with proprietary models succeeding most often and some exhibiting cheating under pressure.
Agent-ValueBench is the first dedicated benchmark for agent values, showing they diverge from LLM values, form a homogeneous 'Value Tide' across models, and bend under harnesses and skill steering.
Soohak is a 439-problem mathematician-curated benchmark where frontier LLMs reach at most 30.4% on research math challenges and no model exceeds 50% on refusal for ill-posed problems.
SignSGD provably beats SGD by a factor of d under sparse noise via matched ℓ1-norm upper and lower bounds, with an equivalent result for Muon on matrices, and this predicts faster GPT-2 pretraining.
WildTableBench is the first QA benchmark for naturally occurring table images, where 21 multimodal models were evaluated and only one exceeded 50% accuracy.
AutoMat benchmark shows current LLM coding agents achieve at most 54.1% success when reproducing computational materials science claims from papers.
AutoResearchBench is a new benchmark showing top AI agents achieve under 10% success on complex scientific literature discovery tasks that demand deep comprehension and open-ended search.
HWE-Bench is the first repository-level benchmark for LLM agents on real hardware bug repair, where the best agent fixes 70.7% of 417 tasks but drops below 65% on complex SoC projects.
VoxSafeBench reveals that speech language models recognize social norms from text but fail to apply them when acoustic cues like speaker or scene determine the appropriate response.
Large language models display the identifiable victim effect at roughly twice the human baseline, strongly amplified by instruction tuning and chain-of-thought prompting but inverted by reasoning-specialized models.
OccuBench is a new benchmark for AI agents on real-world occupational tasks via LLM-driven simulators, showing no model dominates all industries, implicit faults are hardest, and larger models with more reasoning perform better.
FashionMV introduces product-level multi-view CIR, a 127K-product dataset built via automated LMM pipeline, and a 0.8B ProCIR model that beats larger baselines on three fashion benchmarks.
X-Value is the first cross-lingual values judgment benchmark that reveals limitations and performance gaps in LLMs across languages and issue categories.
MindEdit-Bench introduces six spatial reasoning tasks from 120 private indoor photo triplets, with two new counterfactual editing tasks where VLMs score 8-31% against 81-97% human accuracy.
OmniCoT is a new panoramic reasoning benchmark with 6.7K eval, 1K real, and 14.3K training examples plus a two-stage SFT+GRPO training method to enforce global 360-degree consistency.
MuseBench shows state-of-the-art MLLMs achieve only 48.29% accuracy on intent-level audiovisual arts understanding versus 87.18% for human experts.
SpreadsheetBench 2 provides 321 expert-validated tasks from authentic business data showing frontier LLMs reach only 34.89% overall accuracy on end-to-end spreadsheet workflows.
Proposes Monotonic Inference Policy Improvement (MIPI) objective and MIPU two-step update framework to address objective misalignment between training and inference policies in LLM reinforcement learning.
Dockerless uses agentic repository exploration to verify patches without execution, enabling SFT and RL training of coding agents that reach 62.0/50.0/35.2% resolve rates on SWE-bench Verified/Multilingual/Pro while matching environment-based results.
NetLLMeval is an emulation-based framework for benchmarking LLM solvers on network admin tasks, with a 24000-run study showing solver architecture lifts a 14B model from 0.43 to 0.88 accuracy and allows local models to match frontier systems.
HG-Bench supplies 500 human-annotated homework samples and a page-aware protocol that measures complete-answer localization (FA) and step-level decomposition (FSm), exposing that no zero-shot VLM exceeds 55% on either metric.
Vibe Calibration uses LLM agents to orchestrate reusable decision-tree Skills distilled from expert knowledge, autonomously calibrating 108/112 qubits in 4.7 hours with 4-5x speedup and transferable workflows.
Agentic Time Machine reconstructs historical web states for offline evaluation of forecasting agents, with a multi-agent framework achieving top ranks on FutureX live and past benchmarks.
citing papers explorer
-
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
LACUNA is a new testbed that injects PII into predefined model parameters to benchmark the localization precision of LLM unlearning methods, revealing that SOTA approaches are imprecise despite strong output performance.
-
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs
Soohak is a 439-problem mathematician-curated benchmark where frontier LLMs reach at most 30.4% on research math challenges and no model exceeds 50% on refusal for ill-posed problems.
-
Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models
Large language models display the identifiable victim effect at roughly twice the human baseline, strongly amplified by instruction tuning and chain-of-thought prompting but inverted by reasoning-specialized models.
-
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment Simulation
OccuBench is a new benchmark for AI agents on real-world occupational tasks via LLM-driven simulators, showing no model dominates all industries, implicit faults are hardest, and larger models with more reasoning perform better.
-
Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective
X-Value is the first cross-lingual values judgment benchmark that reveals limitations and performance gaps in LLMs across languages and issue categories.
-
Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play
MAFP applies fictitious play to LLM multi-agent systems to resolve stance entanglement in competitive decision-making, outperforming single-round and multi-round baselines on tournament strength and robustness.
-
LegalWorld: A Life-Cycle Interactive Environment for Legal Agents
LegalWorld is a life-cycle interactive environment modeling Chinese civil litigation as five causally connected stages grounded in 75,309 judgments, paired with LongJud-Bench for cross-stage agent evaluation.
-
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents
FORT synthesizes shortcut-resistant search tasks by controlling four identified shortcut risks across entity selection, graph construction, question formulation, and refinement, producing training data that yields agents with longer search trajectories and top performance among open-source models on
-
Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs
Moral Trolley Arena shows frontier LLMs produce composite moral preferences that are compressed rather than additive functions of calibrated component act strengths across Moral Foundations Theory.
-
Learning Agentic Policy from Action Guidance
ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.
-
Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness
ProofRank benchmark shows substantial differences in LLM proof quality not captured by correctness, with trade-offs between quality metrics and accuracy.
-
Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
OPHSD uses harness-augmented models as teachers to distill reasoning capabilities into base LLMs, yielding strong standalone performance on classification and math tasks.
-
MolViBench: Evaluating LLMs on Molecular Vibe Coding
MolViBench is the first benchmark designed to evaluate LLMs on generating executable programs for molecular tasks in drug discovery.
-
Training Computer Use Agents to Assess the Usability of Graphical User Interfaces
uxCUA is a trained computer use agent that assesses GUI usability more accurately than larger models by learning to prioritize and execute important user interactions on labeled interface datasets.
-
Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
AHE automates coding-agent harness evolution via component, experience, and decision observability, raising Terminal-Bench 2 pass@1 from 69.7% to 77.0% with cross-benchmark and cross-model transfer.
-
MathDuels: Evaluating LLMs as Problem Posers and Solvers
Self-play between LLMs for problem authoring and solving, scored via Rasch modeling, shows that authoring and solving skills are partially decoupled and that the benchmark difficulty evolves with new models.
-
Many-Tier Instruction Hierarchy in LLM Agents
ManyIH and ManyIH-Bench address instruction conflicts in LLM agents with up to 12 privilege levels across 853 tasks, revealing frontier models achieve only ~40% accuracy.
-
ClawBench: Can AI Agents Complete Everyday Online Tasks?
ClawBench is a benchmark of 153 live-web tasks where AI agents achieve low success rates, e.g. 33.3% for Claude Sonnet 4.6.
-
Learning to Interrupt in Language-based Multi-agent Communication
HANDRAISER learns optimal interruption points in multi-agent LLM communication using estimated future reward and cost, achieving 32.2% lower communication cost with comparable or better task results across games, scheduling, and debate.
-
EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents
EpiBench is a new episodic multi-turn multimodal benchmark where even leading AI agents score only 29.23% on hard tasks requiring cross-paper evidence integration from figures and tables.
-
DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models
DiARC improves LLM performance on ARC-like benchmarks by constructing and training on preference pairs from three types of negative samples while keeping demonstrations fixed.
-
Large Language Models Do Not Always Need Readable Language
BabelTele lets instruction-tuned LLMs keep 99.5% semantic fidelity while compressing text to 27.9% of original length.
-
From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning
The LLM-as-Environment-Engineer framework lets the policy model redesign its own RL environments on the new MAPF-FrozenLake testbed, outperforming larger models and fixed baselines with Qwen3-4B.
-
Civil Court Simulation with Large Language Models
Multi-agent LLM framework simulates Chinese civil trials through five-stage procedures with memory and retrieval, producing judgments strong in liability allocation and multi-item decisions.
-
CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts
CRAFT is a Pareto-front prompt optimizer that allocates scarce LLM validation calls to candidates near the current front using accuracy- and cost-oriented generators plus NSGA-II retention.
-
GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering
GAPD adds dense token-level guidance from gold actions to outcome-based RL for KBQA via mid-anchor matching and outperforms SOTA on WebQSP, GrailQA, and GraphQ.
-
ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
ClinSeekAgent automates active multimodal evidence seeking for clinical reasoning, improving LLM performance on raw EHR and CXR tasks while enabling distillation into smaller models.
-
OProver: A Unified Framework for Agentic Formal Theorem Proving
OProver-32B achieves top Pass@32 scores on MiniF2F, ProverBench, and PutnamBench by combining continued pretraining with iterative agentic proving, retrieval, SFT on repairs, and RL on unresolved cases using a 6.86M-proof dataset.
-
Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making
Frontier LLMs exhibit bias from stigmatizing language in clinical vignettes across four conditions, skewing decisions toward less aggressive management, with limited mitigation from Chain-of-Thought or self-debiasing prompts.
-
Argus: Evidence Assembly for Scalable Deep Research Agents
Argus coordinates a Navigator and multiple Searchers via an evidence graph for deep research, reporting average gains of 5.5 points with one Searcher and 12.7 points with eight parallel Searchers across eight benchmarks, reaching 86.2 on BrowseComp with 64 Searchers.
-
From 0-Order Selection to 2-Order Judgment: Combinatorial Hardening Exposes Compositional Failures in Frontier LLMs
LogiHard hardens reasoning benchmarks by transforming 0-order selection into 2-order judgment, causing 31-56% accuracy drops in 12 frontier LLMs and a 47% drop on zero-shot MMLU, revealing a combinatorial reasoning gap rather than knowledge deficits.
-
Continuous Latent Diffusion Language Model
Cola DLM proposes a hierarchical latent diffusion model that learns a text-to-latent mapping, fits a global semantic prior in continuous space with a block-causal DiT, and performs conditional decoding, establishing latent prior modeling as an alternative to token-level autoregressive language model
-
Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning
A training recipe for tool-integrated reasoning models achieves state-of-the-art open-source results on math benchmarks such as 96.7% and 99.2% on AIME 2025 at 4B and 30B scales by balancing tool-use trajectories and optimizing for pass@k during SFT before stable RLVR.
-
Evaluation Awareness in Language Models Has Limited Effect on Behaviour
Verbalised evaluation awareness in large reasoning models has only small effects on their outputs across safety and alignment tests.
-
When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models
A new benchmark shows LLM first-answer accuracy on procedural arithmetic drops from 63% (5 steps) to 20% (95 steps) due to execution failures like skipped steps and premature answers.
-
CL-bench Life: Can Language Models Learn from Real-Life Context?
CL-bench Life shows frontier language models achieve only 13.8% average success on real-life context tasks, with the best model at 19.3%.
-
MAIC-UI: Making Interactive Courseware with Generative UI
MAIC-UI provides a zero-code authoring system for generating and iteratively editing interactive courseware from educational materials via structured analysis and incremental generation, with lab and classroom evaluations showing usability gains and learning improvements.
-
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
VLAA-GUI adds mandatory visual verifiers, multi-tier loop breakers, and on-demand search to GUI agents, reaching 77.5% on OSWorld and 61.0% on WindowsAgentArena with some models exceeding human performance.
-
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
GSQ uses Gumbel-Softmax to optimize scalar quantization grids for LLMs, closing most of the accuracy gap to vector methods like QTIP at 2-3 bits per parameter while using symmetric scalar grids compatible with existing kernels.
-
ComPASS: Towards Personalized Agentic Social Support via Tool-Augmented Companionship
ComPASS creates tool-augmented LLM agents for substantive social support, releases the first personalized benchmark ComPASS-Bench, and fine-tunes ComPASS-Qwen to outperform its base model while matching larger LLMs.
-
Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization
Kernel-Smith combines evolutionary search with RL post-training to generate optimized GPU kernels, achieving SOTA speedups on KernelBench that beat Gemini-3.0-pro and Claude-4.6-opus on NVIDIA Triton and generalize to MetaX MACA.
-
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
A 35B MoE agent model trained on 45K-token trajectories via three-stage SFT and domain-routed distillation achieves leading or competitive scores against 1T models on SEAL-0, IFBench, HiPhO, FrontierScience-Olympiad and MolBench-Bind.
-
Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety
Yuvion LLM applies adversarially aware training and introduces the YLRE benchmark set, claiming superior safety robustness over larger models on multiple tasks.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
-
Evaluating Stochastic Collapse and Implicit Bias in Multimodal Large Language Models
MLLMs show stochastic collapse with top-1 probabilities up to 97% and low randomness indices when choosing among equivalent options.
-
VLMs May Not Globally Enhance Human Alignment over LLMs During Natural Reading
Multimodal pretraining does not provide a uniform global advantage over language-only pretraining in aligning model representations with human fMRI and eye-tracking data during natural reading, though selective advantages emerge for visually semantic sentences.
-
DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning
DVAO dynamically weights multi-objective advantages by rollout-group reward variance to bound magnitudes, add cross-objective regularization, and outperform static baselines on math and tool-use tasks with Qwen models.
-
CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection
CompactAttention accelerates chunked-prefill attention via Block-Union KV Selection, delivering up to 2.72x speedup at 128K context on LLaMA-3.1-8B while matching dense accuracy on RULER.
-
Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale
Technical report announcing Ling-2.6 and Ring-2.6 models with hybrid linear attention, evolutionary CoT, and KPop RL for efficient agentic intelligence at scale.
-
Reinforcement Learning for LLM-based Multi-Agent Systems through Orchestration Traces
This survey organizes RL for LLM multi-agent systems into reward families, credit units, and five orchestration sub-decisions, notes the absence of explicit stopping-decision training in its paper pool, and releases a tagged corpus.