arXiv AI
1d ago
From Contexts to Values: Context-Dependent Defeat in Abstract Argumentation
arXiv:2608. 15536v1 Announce Type: new Abstract: In value-based argumentation, an audience's ordering of values decides which attacks succeed as defeats.
Choosing the Lens: Strategic Perspective Activation in Context-Dependent Argumentation
arXiv:2605. 31581v2 Announce Type: replace Abstract: The same arguments often need to be evaluated under different external regimes.
Related stories
arXiv AI
Jun 2
Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory
arXiv:2604. 03588v3 Announce Type: replace Abstract: AI agents operating over extended time horizons accumulate experiences that serve multiple concurrent goals, and must often maintain conflicting interpretations of the same events.
arXiv Machine Learning
2d ago
Identifiability and Order-Dimension Limits of In-Context Learning on Partial Orders
arXiv:2608. 14004v1 Announce Type: new Abstract: In-context learning is commonly formalized as inference from examples of a function.
arXiv Machine Learning
Aug 4
OTAP: Structure-Aware Optimal Transport for Evaluating Planning and Execution in Agent Trajectories
arXiv:2607. 17082v2 Announce Type: replace-cross Abstract: Large language model agents solve tasks by generating trajectories that interleave planning, tool calls, and intermediate results.
arXiv AI
Jul 24
Robust Critics: Defending LLMs Against Multi-Turn Attacks
arXiv:2607. 20472v1 Announce Type: new Abstract: When a user asks a language model something harmful, is it a genuine attack or a misunderstood but well-meaning question?
arXiv Machine Learning
Jun 25
Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval
arXiv:2606. 24976v1 Announce Type: cross Abstract: Foundation-model agents in multi-step, open-ended environments frequently suffer from compounding errors, where early mistakes contaminate long-horizon trajectories.
arXiv AI
Jun 10
Decoupling Thought from Speech: Knowledge-Grounded Counterfactual Reasoning for Resilient Multi-Agent Argumentation
arXiv:2606. 10475v1 Announce Type: cross Abstract: Multi-agent debate frameworks have been shown to improve large language model performance in convergent tasks, but they are currently optimized in a way that heavily favors final output accuracy rather than stability of the process.
arXiv Machine Learning
Aug 10
Sharding Prevents LLM Oversight Failures and Adversarial Exploitation
arXiv:2608. 06422v1 Announce Type: new Abstract: Giving an LLM judge more compute does not necessarily make it check more requirements.
Hugging Face Trending Papers
Jun 28
Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense
Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists. We evaluate five defense paradigms (no defense, static steering, CAST, AlphaSteer, probe-gated) across seven instruction-tuned models (7-31B) and five attack types (GCG, AutoDAN, DeepInception, prefilling, intent laundering).
arXiv AI
Jun 30
Closing the Activation-Cone Blind Spot: Response-Time Probing and Unified Defense
arXiv:2606. 29441v1 Announce Type: cross Abstract: Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists.
arXiv AI
Jun 16
Constitutional Value Potentials: reading and steering internal priority margins in language models
arXiv:2606. 15420v1 Announce Type: cross Abstract: A constitution tells a language model what to value, but little tells us whether it does.
arXiv AI
Jul 3
GroundEval: A Deterministic Replacement for LLM-as-Judge in Stateful Agent Evaluation
arXiv:2606. 22737v2 Announce Type: replace Abstract: Before letting an agent operate over real context, can you prove it used the right evidence?